Developer-tools MCP server

Reticle

Version history of discovered tools, schemas, and declared agent authority.

View watchlist

DistributionDistribution: npm
Package@reticlehq/server
Latest analyzed version3.10.6
Current tool count10
Latest analysisNov 16, 2026
Package source

OBSERVED INTERFACE

Capability surface

Modelara’s observed declarations are shown separately from its derived effect classifications.

3 releases analyzed3.10.4 → 3.10.6Latest: 3.10.6
  • read4
  • write6
  • destructive0
  • unknown0

Unknown means Valyd could not determine the capability's effect confidently from the declared interface and static evidence. It is not treated as safe.

Package
@reticlehq/server@3.10.6
Registry
npm
Published
Nov 15, 2026
Integrity
sha512-c5RXl+Fvn9yO6TClGSVRrzLYig6jCLX5wXiGRTsEbzAIZcLForU7yl7x8QpxJOK2Nd4hza5vY/xaVSwy5vrIhw==
Analyzer
modelara v0.1.8 · policy not recorded
Repository
https://github.com/reticlehq/reticle

10 capabilities

CapabilityTypeDerived effectFirst observed in Valyd coverageLast changed
reticle_actreticlehq-reticle:tool:reticle_act
Observed interface and hashes

Act WITHOUT checking the result — if the action is supposed to cause something, use reticle_act_and_wait { until } instead and get the verdict in the same call. e.g. {"ref":"e42","action":"fill","args":{"value":"hello"}}

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "action": {
      "description": "Action to perform.",
      "enum": [
        "click",
        "dblclick",
        "hover",
        "focus",
        "blur",
        "fill",
        "type",
        "clear",
        "select",
        "check",
        "uncheck",
        "submit",
        "press",
        "upload",
        "scrollIntoView",
        "scroll",
        "drag",
        "insertText",
        "tap",
        "zoom"
      ],
      "type": "string"
    },
    "args": {
      "additionalProperties": {},
      "description": "Action-specific arguments: { value } for fill/select (select also drives an ARIA combobox: it opens it and clicks the option by its label), { text } for type/p…",
      "propertyNames": {
        "type": "string"
      },
      "type": "object"
    },
    "burst": {
      "description": "ms gap between dispatches, to provoke an ordering race (try 50).",
      "maximum": 500,
      "minimum": 0,
      "type": "number"
    },
    "detail": {
      "description": "\"compact\" keeps only the deciding fields.",
      "enum": [
        "compact",
        "full"
      ],
      "type": "string"
    },
    "onDeviation": {
      "description": "What to do when a step's `expect` does not hold.",
      "enum": [
        "halt",
        "continue"
      ],
      "type": "string"
    },
    "ref": {
      "description": "Element ref (e.g. 'e42') from reticle_look { action: \"page\" }/reticle_look { action: \"find\" } — stable until the element leaves the DOM, so no re-snapshot between actions.",
      "type": "string"
    },
    "refuseWhenThrottled": {
      "description": "Throw instead of silently sending synthetic events when the tab is throttled/backgrounded.",
      "type": "boolean"
    },
    "sessionId": {
      "description": "Target a specific tab. Omit unless you mean one — see instructions.",
      "type": "string"
    },
    "steps": {
      "description": "Ordered list of { ref | target, action, args?, expect? } objects.",
      "items": {
        "additionalProperties": {},
        "propertyNames": {
          "type": "string"
        },
        "type": "object"
      },
      "type": "array"
    },
    "target": {
      "additionalProperties": {},
      "description": "Find the element and act on it in ONE call, instead of a reticle_look { action: \"find\" } round trip first: { testid } | { text } | { role, name } | { label }.",
      "propertyNames": {
        "type": "string"
      },
      "type": "object"
    },
    "timeout_ms": {
      "description": "Per-step timeout in milliseconds.",
      "maximum": 55000,
      "minimum": 0,
      "type": "integer"
    }
  },
  "type": "object"
}
sha256:b6f9af6fa315828fcdad198a6e6a1e0d3219d14ba7c963c608abd3a3b8d8e6f9

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:104c0cf2f0508a6bd4e4069bd1cd4ce0a4333fd12caa797c83154375f3ea2b24

Interface hash: sha256:cff0371a9367dcec3bc313aca64ee18f2237f7297f8ed55b3a222d6c46a1b45d

Other observed Modelara metadata
{
  "id": "mcp:reticle/reticle_act",
  "source": {
    "type": "mcp",
    "server": "reticle",
    "operation": "reticle_act"
  },
  "declared": {
    "read_only": "false",
    "destructive": "false",
    "idempotent": "false",
    "open_world": "false"
  },
  "safety": {
    "idempotent": "false",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:6739407eb96457b68522b97f0cf0b69d0e2ed6aaa6d831b0cf8be1293d093220"
}
toolwrite3.10.4No change observed
reticle_act_and_waitreticlehq-reticle:tool:reticle_act_and_wait
Observed interface and hashes

Act on a ref, then wait for a predicate to hold — one hop for the act->observe->assert loop. e.g. {"ref":"e42","action":"click","until":{"kind":"signal","name":"todos:loaded"}}

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "action": {
      "description": "Action to perform.",
      "enum": [
        "click",
        "dblclick",
        "hover",
        "focus",
        "blur",
        "fill",
        "type",
        "clear",
        "select",
        "check",
        "uncheck",
        "submit",
        "press",
        "upload",
        "scrollIntoView",
        "scroll",
        "drag",
        "insertText",
        "tap",
        "zoom"
      ],
      "type": "string"
    },
    "args": {
      "additionalProperties": {},
      "description": "Action-specific arguments: { value } for fill/select (select also drives an ARIA combobox: it opens it and clicks the option by its label), { text } for type/p…",
      "propertyNames": {
        "type": "string"
      },
      "type": "object"
    },
    "detail": {
      "description": "\"compact\" keeps only the deciding fields.",
      "enum": [
        "compact",
        "full"
      ],
      "type": "string"
    },
    "durable": {
      "description": "After a yes, reload and require the element/text/state part of `until` to hold again.",
      "type": "boolean"
    },
    "intent": {
      "description": "What this change is meant to make true — as a durable statement ABOUT THE PRODUCT, or the id of an intent you already declared.",
      "type": "string"
    },
    "predicate": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "additionalProperties": {},
          "propertyNames": {
            "type": "string"
          },
          "type": "object"
        }
      ],
      "description": "Predicate object: { kind, ...fields }. kind is one of element | text | net | route | console | animation | signal | state | settled | compare | allOf | anyOf | not. Bug-catching options: net.count (exact request count — catches double-submit), net.bodyMatches (a JSON field match on what the SERVER answered, keyed by the field: { status: \"completed\" }, never { field, value }; a dotted key reaches a nested field; because a substring of the body matches key names too), net.requestBodyMatches (the same on what the UI SENT — the verdict for \"applying this filter actually puts it in the payload\"), compare (page text vs server answer, no expected value: { left:{from:\"text\",scope}, right:{from:\"net\",urlContains,path}, as:\"number\" }), console.absent:true (action completed with a CLEAN console), absent:true on element/text (gone from the DOM; add visible:true for \"not shown\"). Call reticle_tools for the full field grammar of a kind."
    },
    "ref": {
      "description": "Element ref (e.g. 'e42') from reticle_look { action: \"page\" }/reticle_look { action: \"find\" } — stable until the element leaves the DOM, so no re-snapshot between actions.",
      "type": "string"
    },
    "refuseWhenThrottled": {
      "description": "Throw if the tab is throttled.",
      "type": "boolean"
    },
    "sessionId": {
      "description": "Target a specific tab. Omit unless you mean one — see instructions.",
      "type": "string"
    },
    "target": {
      "additionalProperties": {},
      "description": "Find the element and act on it in ONE call, instead of a reticle_look { action: \"find\" } round trip first: { testid } | { text } | { role, name } | { label }.",
      "propertyNames": {
        "type": "string"
      },
      "type": "object"
    },
    "timeout_ms": {
      "description": "Maximum wait time in milliseconds.",
      "maximum": 55000,
      "minimum": 0,
      "type": "integer"
    },
    "until": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "additionalProperties": {},
          "propertyNames": {
            "type": "string"
          },
          "type": "object"
        }
      ],
      "description": "Predicate object: { kind, ...fields }. kind is one of element | text | net | route | console | animation | signal | state | settled | compare | allOf | anyOf | not."
    }
  },
  "required": [
    "action"
  ],
  "type": "object"
}
sha256:83d73fb9fb326f18331d5db192566fb63f861a78323e4bce97b685189d1fd6e5

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:0ae0ab47c77d8b2c47006237bea4baf66a1e219e5c16d723a929482033319316

Interface hash: sha256:3286db3a85e1cff88fec2a0d075681cfbd3ec09fc7be05754189767641bec6ec

Other observed Modelara metadata
{
  "id": "mcp:reticle/reticle_act_and_wait",
  "source": {
    "type": "mcp",
    "server": "reticle",
    "operation": "reticle_act_and_wait"
  },
  "declared": {
    "read_only": "false",
    "destructive": "false",
    "idempotent": "false",
    "open_world": "false"
  },
  "safety": {
    "idempotent": "false",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:51a78e0fdbe10711f86bd52e4f0ce3b596f7dc3306f57303d4118a4941b36f5b"
}
toolwrite3.10.4No change observed
reticle_assertreticlehq-reticle:tool:reticle_assert
Observed interface and hashes

Prove a consequence, by action: "now" evaluates a predicate against the window that already exists, "wait" waits for one to become true within a budget. e.g. {"action":"now"}

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "action": {
      "description": "Which operation to run.",
      "enum": [
        "now",
        "wait"
      ],
      "type": "string"
    },
    "detail": {
      "description": "\"compact\" keeps only the deciding fields.",
      "enum": [
        "compact",
        "full"
      ],
      "type": "string"
    },
    "intent": {
      "description": "What this change is meant to make true — as a durable statement ABOUT THE PRODUCT, or the id of an intent you already declared.",
      "type": "string"
    },
    "predicate": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "additionalProperties": {},
          "propertyNames": {
            "type": "string"
          },
          "type": "object"
        }
      ],
      "description": "Predicate object: { kind, ...fields }. kind is one of element | text | net | route | console | animation | signal | state | settled | compare | allOf | anyOf | not."
    },
    "sessionId": {
      "description": "Target a specific tab. Omit unless you mean one — see instructions.",
      "type": "string"
    },
    "since": {
      "description": "Cursor (a number) from a prior act or observe result.",
      "maximum": 9007199254740991,
      "minimum": 0,
      "type": "integer"
    },
    "timeout_ms": {
      "anyOf": [
        {
          "description": "If > 0, wait up to this many milliseconds before failing. Default: 0 (evaluate once). Capped at 55000: your MCP client aborts the request before a longer wait can return, so a bound above this would be advertised and not deliverable. To outlast it, poll — several short waits, each of which returns a verdict.",
          "maximum": 55000,
          "minimum": 0,
          "type": "integer"
        },
        {
          "description": "Maximum wait in milliseconds. Default: 4000, up to 600000. One call waits at most 55000 ms, because your MCP client aborts a longer request; past that it returns resume_ms, and you call again with timeout_ms: resume_ms, the same predicate, the same since, and the same intent to keep waiting.",
          "maximum": 600000,
          "minimum": 0,
          "type": "integer"
        }
      ],
      "description": "For action \"now\": If > 0, wait up to this many milliseconds before failing."
    },
    "until": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "additionalProperties": {},
          "propertyNames": {
            "type": "string"
          },
          "type": "object"
        }
      ],
      "description": "Predicate object: { kind, ...fields }. kind is one of element | text | net | route | console | animation | signal | state | settled | compare | allOf | anyOf | not."
    }
  },
  "type": "object"
}
sha256:aed15742f26bf5beb47a852549cc9d9a07edfea31e0c9a17739852fceec28658

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:6abcfb45b035021a5f8a6c92e41bcf1a1140e786ecdb48b40f3b9f6e64ad65c4

Interface hash: sha256:5144976764e702f9c43b5b9bcfcb8be96f819b9482013f9480fbfa1112d7ac92

Other observed Modelara metadata
{
  "id": "mcp:reticle/reticle_assert",
  "source": {
    "type": "mcp",
    "server": "reticle",
    "operation": "reticle_assert"
  },
  "declared": {
    "read_only": "true",
    "destructive": "false",
    "idempotent": "false",
    "open_world": "false"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:1899909dc4206dbb8786fa96cdac8556e9a69d5b72ecea2f6b2cb9d06b27206b"
}
toolread3.10.4No change observed
reticle_lookreticlehq-reticle:tool:reticle_look
Observed interface and hashes

Read the page, by action: "page" is the semantic snapshot of what is rendered, "find" resolves a locator (testid/role/text/component) to refs you can act on, "… e.g. {"action":"find","by":"testid","value":"submit"}

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "action": {
      "description": "Which operation to run.",
      "enum": [
        "page",
        "find",
        "element",
        "state"
      ],
      "type": "string"
    },
    "alt": {
      "description": "Predicate spelling of by/value.",
      "type": "string"
    },
    "attrs": {
      "description": "Attribute NAMES to return per match, e.g. ['href'] for links, ['src'] for images.",
      "items": {
        "type": "string"
      },
      "type": "array"
    },
    "audit": {
      "description": "Also measure the page for what a person would see broken: text cut off with no ellipsis, controls drawn over each other, text under WCAG contrast.",
      "type": "boolean"
    },
    "by": {
      "description": "Query strategy.",
      "enum": [
        "role",
        "text",
        "label",
        "placeholder",
        "testid",
        "alt",
        "component"
      ],
      "type": "string"
    },
    "charts": {
      "description": "Also read each SVG chart as geometry: every bar, dot, line and slice as its box in percent of the chart box, with no colour.",
      "type": "boolean"
    },
    "count_only": {
      "description": "Return just { count } (no element descriptors) — use when you only need \"how many match?\" and not their refs.",
      "type": "boolean"
    },
    "depth": {
      "description": "Collapse anything deeper than N levels to a size marker — avoids huge outputs for large stores.",
      "exclusiveMinimum": 0,
      "maximum": 256,
      "type": "integer"
    },
    "diff": {
      "description": "Return only what changed since your last snapshot of the same scope/mode (mode:delta|unchanged).",
      "type": "boolean"
    },
    "ids": {
      "description": "Add [testid=…] to each control that carries one: a stable identity for a harness mapping the app.",
      "type": "boolean"
    },
    "label": {
      "description": "Predicate spelling of by/value.",
      "type": "string"
    },
    "limit": {
      "description": "Cap descriptors to the first N.",
      "maximum": 2000,
      "minimum": 0,
      "type": "integer"
    },
    "mode": {
      "description": "full = all elements; interactive = only clickable/focusable elements; status = only route + title.",
      "enum": [
        "full",
        "interactive",
        "status"
      ],
      "type": "string"
    },
    "name": {
      "description": "Exact accessible-name filter - narrows results when `by` is role and the page has many elements of that role.",
      "type": "string"
    },
    "path": {
      "description": "Dot-path into the store (e.g. 'captionCache.v3').",
      "type": "string"
    },
    "placeholder": {
      "description": "Predicate spelling of by/value.",
      "type": "string"
    },
    "ref": {
      "description": "Element ref (e.g. 'e42') from reticle_look { action: \"page\" }/reticle_look { action: \"find\" } — stable until the element leaves the DOM, so no re-snapshot between actions.",
      "type": "string"
    },
    "role": {
      "description": "Predicate spelling of by/value.",
      "type": "string"
    },
    "scope": {
      "description": "CSS selector or element ref to restrict the snapshot to a subtree.",
      "type": "string"
    },
    "self": {
      "description": "Return the `scope` element ITSELF instead of searching inside it.",
      "type": "boolean"
    },
    "sessionId": {
      "description": "Target a specific tab. Omit unless you mean one — see instructions.",
      "type": "string"
    },
    "store": {
      "description": "Registered store name (e.g. 'workspace').",
      "type": "string"
    },
    "testid": {
      "description": "Predicate spelling of by/value.",
      "type": "string"
    },
    "text": {
      "description": "Predicate spelling of by/value.",
      "type": "string"
    },
    "value": {
      "description": "Query value for the selected strategy (e.g. by=role value=button, or by=testid value=submit-btn).",
      "type": "string"
    }
  },
  "type": "object"
}
sha256:36877ce93f9dbacb45087b0284556153b04a303d6d30dd41c295a8095ef12fb8

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:5cb92aa6dbbad39221ba0f556cd4f5d5b6836c82581517ff07bfb9fbd0925bb8

Interface hash: sha256:74f76b51dd2fb5a16a0992ac633c37f2ae2c89234d195e1108264e2b26d79a45

Other observed Modelara metadata
{
  "id": "mcp:reticle/reticle_look",
  "source": {
    "type": "mcp",
    "server": "reticle",
    "operation": "reticle_look"
  },
  "declared": {
    "read_only": "true",
    "destructive": "false",
    "idempotent": "false",
    "open_world": "false"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:337e6541ddc91ba244670c07c044ad8e5e513d4ff342d4508c17f33a294c8c28"
}
toolread3.10.4No change observed
reticle_navigatereticlehq-reticle:tool:reticle_navigate
Observed interface and hashes

Navigate the connected browser tab to a URL, or reload it in place with { reload: true } (add { hard: true } to bypass the cache). e.g. {"url":"/settings"}

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "hard": {
      "description": "With reload:true, bypass the browser cache (Cmd+Shift+R) on a leased tab.",
      "type": "boolean"
    },
    "reload": {
      "description": "Reload the current page instead of navigating (replaces the former standalone refresh tool).",
      "type": "boolean"
    },
    "sessionId": {
      "description": "Target a specific tab. Omit unless you mean one — see instructions.",
      "type": "string"
    },
    "timeout_ms": {
      "description": "How long to wait for the page to come back (the SDK reconnecting at the new URL, or under the same id on a reload) before answering confirmed:false.",
      "maximum": 55000,
      "minimum": 0,
      "type": "integer"
    },
    "url": {
      "description": "The URL to navigate to.",
      "type": "string"
    }
  },
  "type": "object"
}
sha256:1cbc786e5c03708b6b4da15515309256f642c9a31b20060840f73578c3cfc47e

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:0f4a81f35c7037dec436a57f4077715af56b871f653af9eac8bc72e6a56e6e20

Interface hash: sha256:b1b0d793a14f1fb852babeeef3a773455494dc9f404eff84c013f1b1c50c2072

Other observed Modelara metadata
{
  "id": "mcp:reticle/reticle_navigate",
  "source": {
    "type": "mcp",
    "server": "reticle",
    "operation": "reticle_navigate"
  },
  "declared": {
    "read_only": "false",
    "destructive": "false",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "false",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:14b12f96f43b34b558ba50e0af8dc7f36e9c3a5a5b8521da8d94182cac5985de"
}
toolwrite3.10.4No change observed
reticle_observereticlehq-reticle:tool:reticle_observe
Observed interface and hashes

What the app DID, by action: "events" is the reaction window since a cursor, "network" the requests it made, "console" what it logged. e.g. {"action":"events"}

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "action": {
      "description": "Which operation to run.",
      "enum": [
        "events",
        "network",
        "console"
      ],
      "type": "string"
    },
    "actionId": {
      "description": "Keep only events attributed to this action — answers \"what did action N cause\".",
      "type": "string"
    },
    "assets": {
      "description": "List the dev server's own successful asset GETs (modules, styles, maps, Vite plumbing).",
      "type": "boolean"
    },
    "bodies": {
      "description": "Body detail.",
      "type": "boolean"
    },
    "filters": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "items": {
            "type": "string"
          },
          "type": "array"
        }
      ],
      "description": "Event type allowlist — the cheapest way to shrink a large timeline."
    },
    "level": {
      "description": "Log level filter.",
      "enum": [
        "log",
        "warn",
        "error",
        "info"
      ],
      "type": "string"
    },
    "limit": {
      "description": "Cap descriptors to the first N.",
      "maximum": 2000,
      "minimum": 0,
      "type": "integer"
    },
    "max_events": {
      "description": "Cap the timeline to the most recent N events.",
      "maximum": 2000,
      "minimum": 0,
      "type": "integer"
    },
    "method": {
      "description": "HTTP method filter: GET | POST | PUT | DELETE | PATCH etc.",
      "type": "string"
    },
    "ok": {
      "description": "Outcome filter: false keeps only calls that FAILED, true only those that succeeded.",
      "type": "boolean"
    },
    "sessionId": {
      "description": "Target a specific tab. Omit unless you mean one — see instructions.",
      "type": "string"
    },
    "since": {
      "description": "Cursor (a number) from a prior act or observe result.",
      "maximum": 9007199254740991,
      "minimum": 0,
      "type": "integer"
    },
    "status": {
      "description": "HTTP status code filter (e.g. 200, 404, 500).",
      "maximum": 599,
      "minimum": 100,
      "type": "integer"
    },
    "until": {
      "description": "Upper cursor bound.",
      "maximum": 9007199254740991,
      "minimum": 0,
      "type": "integer"
    },
    "urlContains": {
      "description": "Substring that the request URL must contain.",
      "type": "string"
    },
    "window_ms": {
      "description": "Time window to look back, in ms (must be > 0).",
      "exclusiveMinimum": 0,
      "maximum": 120000,
      "type": "integer"
    }
  },
  "type": "object"
}
sha256:3c65962ea3a651bf3286fd959299ea4a96fa79ec3b73bf68439e9a77ac0cff3f

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:99a086892d76d273744b7db274d67dadb6387bd2450a8cb4f04b9fd7d0da77c6

Interface hash: sha256:b0d70c5d0e697efa12c7215be22f7fe3b5ce46f7ea905a675d3604d595fe9fe2

Other observed Modelara metadata
{
  "id": "mcp:reticle/reticle_observe",
  "source": {
    "type": "mcp",
    "server": "reticle",
    "operation": "reticle_observe"
  },
  "declared": {
    "read_only": "true",
    "destructive": "false",
    "idempotent": "false",
    "open_world": "false"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:6d0fb231efdadf6e30fe0a8cb0a8ac10dfc087fbb61c177cee96b96976af7ec4"
}
toolread3.10.4No change observed
reticle_runreticlehq-reticle:tool:reticle_run
Observed interface and hashes

Invoke any Reticle tool by name (discover names/params first with reticle_tools). On an unknown tool or bad arguments it returns the available names or the tool's params, so you can correct and retry.

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "args": {
      "additionalProperties": {},
      "description": "Arguments object for that tool.",
      "propertyNames": {
        "type": "string"
      },
      "type": "object"
    },
    "sessionId": {
      "description": "Target tab for the invoked tool. Forwarded to it — an explicit args.sessionId wins.",
      "type": "string"
    },
    "tool": {
      "description": "Tool name to invoke, e.g. reticle_clock.",
      "type": "string"
    }
  },
  "required": [
    "tool"
  ],
  "type": "object"
}
sha256:1c8c0a530c9e4144fdf00dfe3ea6a2b570b66812f40a92b6abc80dc308b5e456

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:3676e87f4ffe1a2bdd8146c9bdd7060df3f173506b3922c324f88bb6ed1b359f

Interface hash: sha256:b14e0797b1b8fd895b244d106f16ea331e05f9423380d83142dc1598db218528

Other observed Modelara metadata
{
  "id": "mcp:reticle/reticle_run",
  "source": {
    "type": "mcp",
    "server": "reticle",
    "operation": "reticle_run"
  },
  "declared": {
    "read_only": "false",
    "destructive": "false",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "false",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:ad31e90fde33179c36a5c6689e554cba3d640fa07ac0c1e6b7008fc9d1ac742d"
}
toolwrite3.10.4No change observed
reticle_sessionreticlehq-reticle:tool:reticle_session
Observed interface and hashes

By action: "list" (the default) shows connected tabs; "yield" is MANDATORY before you stop; "tune" hides or moves the HUD; "feedback" reports a problem. e.g. {"action":"yield","mode":"waiting"}

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "action": {
      "description": "Which operation to run.",
      "enum": [
        "tune",
        "yield",
        "end",
        "resume",
        "messages",
        "review",
        "narrate",
        "account",
        "list",
        "feedback"
      ],
      "type": "string"
    },
    "all": {
      "description": "Include already-resolved marks in the listing (default: pending only).",
      "type": "boolean"
    },
    "claim": {
      "description": "What YOU claim this session showed.",
      "enum": [
        "pass",
        "fail",
        "partial"
      ],
      "type": "string"
    },
    "contact": {
      "description": "An email address for a reply from the maintainers.",
      "type": "string"
    },
    "currentApproach": {
      "description": "How you work around it TODAY.",
      "type": "string"
    },
    "disconnect": {
      "description": "Also detach this page for good (needs sessionId).",
      "type": "boolean"
    },
    "hud": {
      "description": "Hide, show or remove the HUD, or move it to a corner.",
      "enum": [
        "shown",
        "hidden",
        "removed",
        "top-left",
        "top-right",
        "bottom-left",
        "bottom-right"
      ],
      "type": "string"
    },
    "idleEndMs": {
      "description": "Idle window in milliseconds after which the panel shows WAITING (your turn).",
      "maximum": 3600000,
      "minimum": 0,
      "type": "integer"
    },
    "impact": {
      "description": "What measurably improves — fewer tool calls, fewer retries, a verdict that stops being ambiguous, a flow you currently cannot verify at all.",
      "type": "string"
    },
    "kind": {
      "description": "bug = a Reticle tool returned a wrong or broken result; gap = Reticle could not observe something you needed at all; ambiguity = the verification ran but you c…",
      "enum": [
        "bug",
        "gap",
        "ambiguity",
        "feature_request",
        "improvement",
        "experience"
      ],
      "type": "string"
    },
    "level": {
      "description": "Display severity.",
      "enum": [
        "info",
        "warn",
        "error"
      ],
      "type": "string"
    },
    "mode": {
      "description": "\"waiting\" = turn done, will resume; \"ask\" = blocked, need the human to answer.",
      "enum": [
        "waiting",
        "ask"
      ],
      "type": "string"
    },
    "model": {
      "description": "The model you are running (e.g. \"claude-opus-4\", \"gpt-5\").",
      "type": "string"
    },
    "need": {
      "description": "The GOAL behind a request, not the request itself.",
      "type": "string"
    },
    "note": {
      "description": "For mode:\"ask\", the question to show the human on the panel.",
      "type": "string"
    },
    "rating": {
      "description": "How well it worked, 1-5, with an `experience`.",
      "maximum": 5,
      "minimum": 1,
      "type": "integer"
    },
    "resolve": {
      "description": "A mark id (e.g. \"m1\") to retire after you have fixed it.",
      "type": "string"
    },
    "sessionId": {
      "description": "Target a specific tab. Omit unless you mean one — see instructions.",
      "type": "string"
    },
    "summary": {
      "description": "One sentence: what this session proved.",
      "type": "string"
    },
    "text": {
      "description": "Short sentence describing your next action, shown on the presenter HUD for the developer watching.",
      "type": "string"
    },
    "trace": {
      "description": "The literal tool calls and responses that led here, so the failure can be reproduced without guessing.",
      "type": "string"
    }
  },
  "type": "object"
}
sha256:bf210508e67e1700ef521232fbde3cc97021e9fb54f00e4e6d30d9a3be2ec80b

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:b8ee4b7f25c0a263f38d5c2b3bb6c255bd2f0ed51a6471daa08386589c4a97e0

Interface hash: sha256:507c16f785a19b16f7f834ac70064bc8900519b20b01f9984681079febe18c7c

Other observed Modelara metadata
{
  "id": "mcp:reticle/reticle_session",
  "source": {
    "type": "mcp",
    "server": "reticle",
    "operation": "reticle_session"
  },
  "declared": {
    "read_only": "false",
    "destructive": "false",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "false",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:a9e8ac9320ec0277d5a5fd74aa54e65bbea5ce2fc69cf6a3a2d11ac3ebe74c8c"
}
toolwrite3.10.4No change observed
reticle_toolsreticlehq-reticle:tool:reticle_tools
Observed interface and hashes

Discover Reticle tools on demand. Call with no arguments to list every tool (name + one-line summary); call with names:["reticle_screenshot", …] to load full descriptions and parameters for specific tools. Then invoke them with reticle_run. This avoids paying for every tool definition on every turn. To make a verification REUSABLE (record once, replay free forever), the flow workflow lives here: reticle_record{action:"start"} → act → reticle_record{action:"stop"} → reticle_flow_save → reticle_verify{action:"flows"} (and reticle_verify { action: "heal" } on drift). Load those names when you want to save or re-run a flow.

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "action": {
      "const": "list",
      "description": "\"list\": the catalogue, same as no arguments.",
      "type": "string"
    },
    "name": {
      "description": "One tool name: the same as names:[name].",
      "type": "string"
    },
    "names": {
      "description": "Tool names to load full params for. Omit to list all tools with summaries.",
      "items": {
        "type": "string"
      },
      "type": "array"
    }
  },
  "type": "object"
}
sha256:3bac8616efe7a65d97cdbc1cf173fdafa219997d9f5ac8c12c16372c05fedb28

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:e16838a98a081be86af51e2d4574eb5e204813a6b595a436d8c169320d63822a

Interface hash: sha256:04414bdfa82a6fd4103f10eb14a0018b0be61af5794e10210c168b45822efe3d

Other observed Modelara metadata
{
  "id": "mcp:reticle/reticle_tools",
  "source": {
    "type": "mcp",
    "server": "reticle",
    "operation": "reticle_tools"
  },
  "declared": {
    "read_only": "true",
    "destructive": "false",
    "idempotent": "false",
    "open_world": "false"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:5126036ed3eb6e1a07c072cbbe99c22d009a1b2236dc5ce87542528d4529544c"
}
toolread3.10.4No change observed
reticle_verifyreticlehq-reticle:tool:reticle_verify
Observed interface and hashes

The Reticle Harness is { action: "explore" }: when the user asks for the Harness, or asks Reticle to drive and verify the app for you, call it and do not drive… e.g. {"action":"change","files":["src/App.tsx"]}

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "action": {
      "description": "Which operation to run.",
      "enum": [
        "change",
        "flows",
        "affected",
        "coverage",
        "crawl",
        "explore",
        "mutate",
        "heal",
        "compare"
      ],
      "type": "string"
    },
    "app": {
      "description": "Also fold into the app-wide ledger; returns `app.levels`, `app.holes` and `app.findings`.",
      "type": "boolean"
    },
    "apply": {
      "description": "Write the rebind.",
      "type": "boolean"
    },
    "base": {
      "description": "URL of the build before the change.",
      "type": "string"
    },
    "budgetMs": {
      "description": "Total time budget for the sequential run, in milliseconds (default 240000, below the ~300 s at which common MCP clients stop waiting).",
      "exclusiveMinimum": 0,
      "maximum": 3600000,
      "type": "integer"
    },
    "candidate": {
      "description": "URL of the build to check.",
      "type": "string"
    },
    "confirmDangerous": {
      "description": "Set true to allow destructive controls during this run of the suite only.",
      "type": "boolean"
    },
    "driveId": {
      "description": "The drive id an explore call answered with.",
      "type": "string"
    },
    "exhaustive": {
      "description": "Walk every state it can tell apart, drive each write's failure path and edge cases, fold into the coverage ledger.",
      "type": "boolean"
    },
    "expect": {
      "additionalProperties": {},
      "description": "Predicate it must end in (route, net, state), asserted after.",
      "propertyNames": {
        "type": "string"
      },
      "type": "object"
    },
    "files": {
      "description": "Changed file paths, repo-relative (e.g. [\"src/App.tsx\"]).",
      "items": {
        "type": "string"
      },
      "type": "array"
    },
    "flow": {
      "description": "Alias for `flowName`.",
      "type": "string"
    },
    "flowName": {
      "description": "Flow file name (without .json), from reticle_verify { action: \"flows\" }, which names every saved flow.",
      "type": "string"
    },
    "ignoreHTTPSErrors": {
      "description": "Accept a self-signed or local-CA certificate for parallel flow leases.",
      "type": "boolean"
    },
    "labels": {
      "description": "Verify flows with ANY of these labels.",
      "items": {
        "type": "string"
      },
      "type": "array"
    },
    "maxSteps": {
      "description": "Maximum number of controls to click.",
      "maximum": 500,
      "minimum": 0,
      "type": "integer"
    },
    "names": {
      "description": "Flow names to verify.",
      "items": {
        "type": "string"
      },
      "type": "array"
    },
    "parallel": {
      "description": "Replay this many affected flows at once (needs the browser pool).",
      "maximum": 32,
      "minimum": 0,
      "type": "integer"
    },
    "persona": {
      "description": "The journey in plain words; \"quoted text\" must show at the end.",
      "type": "string"
    },
    "planId": {
      "description": "Run a plan saved on the dashboard, as it stands.",
      "type": "string"
    },
    "reference": {
      "description": "URL of the build that is right, e.g. main.",
      "type": "string"
    },
    "runId": {
      "description": "The run id a call answered with; pass it to poll that run.",
      "type": "string"
    },
    "say": {
      "description": "With runId: a note to the running Harness.",
      "type": "string"
    },
    "scope": {
      "description": "CSS selector or element ref to restrict crawling to a subtree.",
      "type": "string"
    },
    "secrets": {
      "additionalProperties": {
        "type": "string"
      },
      "description": "Redacted fields' values, this call only, never kept: { \"auth-password\": \"…\" }",
      "propertyNames": {
        "type": "string"
      },
      "type": "object"
    },
    "sessionId": {
      "description": "Target a specific tab. Omit unless you mean one — see instructions.",
      "type": "string"
    },
    "settleMs": {
      "description": "Milliseconds to wait after each click for the app to react.",
      "maximum": 55000,
      "minimum": 0,
      "type": "integer"
    },
    "since": {
      "description": "Git ref to diff against (e.g. \"HEAD~1\", \"main\").",
      "type": "string"
    },
    "skipWrites": {
      "description": "Certify without changing data: hold back every flow with a step that sends a write request (POST, PUT, PATCH, DELETE), and name them in `skippedWrites`.",
      "type": "boolean"
    },
    "stop": {
      "description": "With runId: stop that Harness run.",
      "type": "boolean"
    },
    "wait": {
      "description": "Seconds; default 50.",
      "maximum": 240,
      "minimum": 0,
      "type": "number"
    }
  },
  "required": [
    "action"
  ],
  "type": "object"
}
sha256:368d045bf1647488ffa23c482bbba10ba583eef805e6c3b970cea00633cf42ad

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:4e736d87cdf22a1c84acc5b1ffc6623997a31eca5a1d87e6c1c87dd4313da527

Interface hash: sha256:8dc5afe09363585d790c18e4cdef240e9fb0a405d9570cae56763013277956cc

Other observed Modelara metadata
{
  "id": "mcp:reticle/reticle_verify",
  "source": {
    "type": "mcp",
    "server": "reticle",
    "operation": "reticle_verify"
  },
  "declared": {
    "read_only": "false",
    "destructive": "false",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "false",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:0a9a5eae5c52b270be5950c1abea58a52efff95f3d406a359b4b5ecd77d46a90"
}
toolwrite3.10.4No change observed

STATIC COMPARISONS

Release history

2 release transitions
  1. 0 added0 removed0 schema0 write0 destructive0 unknown

    Nov 16, 2026· Automated static analysis

  2. 0 added0 removed0 schema0 write0 destructive0 unknown

    Nov 16, 2026· Automated static analysis