Reasoning MCP server

OrcaRouter

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

View watchlist

DistributionDistribution: npm
Package@orcarouter/mcp
Latest analyzed version1.1.5
Current tool count4
Latest analysisNov 16, 2026
Package source

OBSERVED INTERFACE

Capability surface

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

3 releases analyzed1.1.3 → 1.1.5Latest: 1.1.5
  • read3
  • write1
  • 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
@orcarouter/mcp@1.1.5
Registry
npm
Published
May 26, 2026
Integrity
sha512-FcxKGCnBNe4Q/uBcvhQbs+BBXBSFaW5MDxoN1N4JW4oO4xpgw80rta0A7/2K/TBNC5XHOSCGTXqQg/y+HrhAtA==
Analyzer
modelara v0.1.8 · policy not recorded
Repository
https://github.com/Continuum-AI-Corp/orcarouter-mcp-server

4 capabilities

CapabilityTypeDerived effectFirst observed in Valyd coverageLast changed
orcarouter_chatcontinuum-ai-corp-orcarouter-mcp:tool:orcarouter_chat
Observed interface and hashes

Send a single-turn chat request to OrcaRouter and return the assistant's response text. Default model is the workspace's auto-router. Use `orcarouter/<name>` for other routers or `<provider>/<model>` for direct calls. For OpenAI reasoning models (gpt-5/o1/o3/...), max_tokens is automatically routed to max_completion_tokens at the wire level. The optional `models` array sets a fallback chain — the primary `model` is tried first, then each entry on failure (5 entries total max, including the primary). Errors are returned as text content with isError:true; common cases include missing API key, rate limits, and upstream provider outages. Requires ORCAROUTER_API_KEY.

Input schema

{
  "additionalProperties": false,
  "properties": {
    "max_tokens": {
      "default": 10000,
      "description": "Maximum tokens to generate (default 10000). Automatically translated to max_completion_tokens for OpenAI reasoning models.",
      "type": "integer"
    },
    "model": {
      "default": "orcarouter/auto",
      "description": "Model to call. Defaults to `orcarouter/auto` — your workspace's seeded auto-router. Use `orcarouter/<name>` for other workspace routers, or `<provider>/<model>` for direct upstream selection (e.g. `openai/gpt-4o-mini`, `anthropic/claude-haiku-4.5`).",
      "type": "string"
    },
    "models": {
      "description": "Optional fallback chain. Models are tried in order if the primary fails. Max 5 entries including the primary.",
      "items": {
        "type": "string"
      },
      "maxItems": 5,
      "minItems": 1,
      "type": "array"
    },
    "prompt": {
      "description": "User message to send (single-turn).",
      "type": "string"
    },
    "system_prompt": {
      "description": "Optional system prompt prepended to the conversation.",
      "type": "string"
    },
    "temperature": {
      "default": 0.7,
      "description": "Sampling temperature (default 0.7).",
      "type": "number"
    }
  },
  "required": [
    "prompt"
  ],
  "type": "object"
}
sha256:85e52293db0a216e345f77789e666b88c060ca94d532d29575953bc70496e2c8

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:ebb76bf1c2c847f2d02a5d8a1fbf903c0207984acf30248af9b3ac8ad703e1aa

Interface hash: sha256:f9db0ee3127df5580234320e6884c774429f40411038455aefe46a021d41288c

Other observed Modelara metadata
{
  "id": "mcp:@orcarouter/mcp/orcarouter_chat",
  "title": "OrcaRouter Chat",
  "source": {
    "type": "mcp",
    "server": "@orcarouter/mcp",
    "operation": "orcarouter_chat"
  },
  "declared": {
    "read_only": "false",
    "destructive": "false",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "false",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:c2351a7e2ee53c780419785f42a66ff1024ca7840aeccae78156dfaa77ecfc02"
}
toolwrite1.1.31.1.4
orcarouter_model_cardcontinuum-ai-corp-orcarouter-mcp:tool:orcarouter_model_card
Observed interface and hashes

Get detailed information about a single model — display name, long description, pricing (per-call and per-million tokens), context window, max output, modalities (input/output), supported endpoints, latency percentiles (p50/p95), and release date. Use this when you already know the model id and want full details; for browsing or filtering across many models use orcarouter_models_list instead. Returns isError:true with a clear hint when the id is not found. Read-only, no API key required.

Input schema

{
  "additionalProperties": false,
  "properties": {
    "model": {
      "description": "Model ref in `provider/slug` form (e.g. `openai/gpt-4o-mini`, `anthropic/claude-haiku-4.5`). Use the exact `id` value returned by orcarouter_models_list.",
      "type": "string"
    }
  },
  "required": [
    "model"
  ],
  "type": "object"
}
sha256:86ad06f045641469a2918bdf92726fb0deb27dfaae0ee1986aa080cd636b7eb9

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:ce5923d698f2518f14341578ae9ca53768c579371502623bef05d18cb9af51ac

Interface hash: sha256:3a7d1dbf083346a5209a311d1aa5bf0103d1ba56a2677850ca0661f466a947a9

Other observed Modelara metadata
{
  "id": "mcp:@orcarouter/mcp/orcarouter_model_card",
  "title": "OrcaRouter Model Card",
  "source": {
    "type": "mcp",
    "server": "@orcarouter/mcp",
    "operation": "orcarouter_model_card"
  },
  "declared": {
    "read_only": "true",
    "destructive": "false",
    "idempotent": "true",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:67cec1e099b6d9a003cd6339b8fcd3cdb00f60f8f59014d7dd74ee881134491d"
}
toolread1.1.31.1.4
orcarouter_models_listcontinuum-ai-corp-orcarouter-mcp:tool:orcarouter_models_list
Observed interface and hashes

List LLM models in the OrcaRouter catalog. Each entry includes id, name, description, owned_by, context_length, supported_endpoint_types, and pricing (both per-token and per-million tokens). Filter by `provider`, `capability`, or `min_context` — filters compose (all conditions must match) and are applied server-side. Discover valid provider ids first with orcarouter_providers_list. Returns the full catalog when called without filters. Read-only, no API key required.

Input schema

{
  "additionalProperties": false,
  "properties": {
    "capability": {
      "description": "Filter to models supporting this capability.",
      "enum": [
        "chat",
        "embedding",
        "image",
        "audio"
      ],
      "type": "string"
    },
    "min_context": {
      "description": "Filter to models with context window at least this large (tokens).",
      "minimum": 1,
      "type": "integer"
    },
    "provider": {
      "description": "Provider id (lowercase, e.g. 'openai', 'anthropic'). Get the full list via orcarouter_providers_list.",
      "type": "string"
    }
  },
  "type": "object"
}
sha256:53bca29a2f164e4cd2b7ba3688cb1f8b4fcaf14fc87ab74b0e90bf14c43fc2bf

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:6fbb16c2ce7e79176deaf736450bf51ec467cc160e57b03037bb7dfe3c3c76f0

Interface hash: sha256:0e70dbd97595f756c98e93aa879f9e605bcbe32657483044a89f9e2f658f2484

Other observed Modelara metadata
{
  "id": "mcp:@orcarouter/mcp/orcarouter_models_list",
  "title": "Browse OrcaRouter Models",
  "source": {
    "type": "mcp",
    "server": "@orcarouter/mcp",
    "operation": "orcarouter_models_list"
  },
  "declared": {
    "read_only": "true",
    "destructive": "false",
    "idempotent": "true",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:29be399dd8b00029647ab1e95ff25eee9db9a602fe0beca464f20ebbc2141eef"
}
toolread1.1.31.1.4
orcarouter_providers_listcontinuum-ai-corp-orcarouter-mcp:tool:orcarouter_providers_list
Observed interface and hashes

List all model providers on OrcaRouter with their `provider_id`, human-readable `display_name`, `icon_url`, and `model_count`. Call this first to discover valid provider ids (e.g. 'openai', 'anthropic', 'google', 'qwen', 'deepseek') which you can then pass to orcarouter_models_list as the `provider` filter. Takes no parameters and returns the same list on every call until the deployment's catalog changes. Read-only, no API key required.

Input schema

{
  "additionalProperties": false,
  "properties": {},
  "type": "object"
}
sha256:fc182e1a69a66dadc6c6ee98df9606d1d4fd90fb51b082083aaa8c230cb4765c

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:d9a11cb82304985d8b2a5fddb562d5ba4f07394ed8b16b65192c19f216acdadd

Interface hash: sha256:f6b787bb12c59e7166478a83d7fc175b7babd0d1299329f4311cdb0f5efa791c

Other observed Modelara metadata
{
  "id": "mcp:@orcarouter/mcp/orcarouter_providers_list",
  "title": "List OrcaRouter Providers",
  "source": {
    "type": "mcp",
    "server": "@orcarouter/mcp",
    "operation": "orcarouter_providers_list"
  },
  "declared": {
    "read_only": "true",
    "destructive": "false",
    "idempotent": "true",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:5a6e56818ea371d71d754ddb5c3e16fc7dfef499cd6a074e95e2cb6b2c86459f"
}
toolread1.1.31.1.4

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