OpenRouter
PYPI · MCP-OPENROUTER
MCP server providing access to 300+ AI models via OpenRouter
Available components
Last scanned (23 hours ago)
Scores higher than 93% of PyPI servers
Category AI and Machine Learning
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security100
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- Runs hatchling.build at install time, a recognised build step with no custom scripting around it. View diagnostics → Pass
- 1 of 19 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency97
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Cryptographically verified build provenance (signed, bound to tsilva/mcp-openrouter). View diagnostics → Pass
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 169 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability69
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 869 tokens (~173/item across 5 items; 5 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management80
- Stability observed for 24 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
- Structured output schemas are declared (80% of tools); any adoption earns full credit.Pass
Tool Safety75
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "chat" implies "send" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
- An AI judge read all 6 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 16 Oct 26 +56
- Malware scan: unverified → pass ▲ security
- Injection markers: unverified → pass ▲ security
- Stability: unverified → 0.80 ▲ functional
- Tool coverage: unverified → 100 ▲ functional
- MCP protocol: unverified → pass ▲ functional
- 13 Oct 26 −15
- Malware scan: pass → unverified ▼ security
- 12 Oct 26 +15
- Malware scan: unverified → pass ▲ security
- 9 Oct 26 −42
- Stability: 0.87 → unverified ▼ security
- Tool safety: pass → unverified ▼ security
- Tool coverage: 100 → unverified ▼ functional
- Capabilities: pass → unverified ▼ functional
- 4 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.
- 2 Oct 26 −2
- Stability: pass → 0.80 functional
- 1 Oct 26 0
- Stability: 0.97 → pass security
- 30 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 16 Oct 2026 · Analysed pypi/mcp-openrouter@1.1.8
Provenance Verified
A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.
| Result | Verified |
|---|---|
| Ecosystem | pypi |
| Reason | Verified |
| Discovered via | Registry attestation endpoint |
| Source repo | tsilva/mcp-openrouter |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/tsilva/mcp-openrouter/.github/workflows/release.yml@refs/heads/main |
| Rekor log index | 1403014433 |
| Predicate type | PyPI publish attestation https://docs.pypi.org/attestations/publish/v1 |
| Subject digest | sha256:ed85cf7d680a8626dcaff547ae50658f663a7dec9ecea3dae0954892c3977bda |
Background: How many MCP packages publish verified provenance →
Install scripts 1 script
| Hook | Tier | Command |
|---|---|---|
| build_backend | allowlisted | hatchling.build |
Background: Why install scripts are a supply-chain risk →
Dependencies 19 packages
| Packages resolved | 19 |
|---|---|
| Stale | 1 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
chat ~340
Send a chat completion request to any OpenRouter model.
| Name | Type | Req | Description |
|---|---|---|---|
| assistant_prefill | – | – | Text to prefill the assistant response with |
| frequency_penalty | – | – | Penalize repeated tokens (-2 to 2) |
| json_mode | boolean | – | If True, request JSON-formatted response (backward compat) |
| max_tokens | – | – | Maximum tokens in response (model default if not specified) |
| messages | – | – | Multi-turn conversation as a list of {role, content} dicts (provide either prompt or messages, not both) |
| model | – | – | Model identifier (e.g., "anthropic/claude-sonnet-4", "openai/gpt-4o"). If not specified, uses DEFAULT_TEXT_MODEL environment variable. |
| presence_penalty | – | – | Penalize tokens already present (-2 to 2) |
| prompt | – | – | User message to send (provide either prompt or messages, not both) |
| provider | – | – | Provider routing control (e.g., {"order": ["Anthropic", "Google"]}) |
| reasoning_effort | – | – | Reasoning effort level: "minimal", "medium", or "high" |
| response_format | – | – | Response format spec, e.g. {"type": "json_schema", ...}. Supersedes json_mode if both provided. |
| seed | – | – | Random seed for deterministic outputs |
| stop | – | – | List of stop sequences |
| system | – | – | Optional system prompt to set context |
| temperature | – | – | Sampling temperature 0-2 (model default if not specified) |
| top_k | – | – | Top-k sampling (number of top tokens to consider) |
| top_p | – | – | Nucleus sampling threshold 0-1 |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
embed ~102
Generate embeddings for text input using an OpenRouter embedding model.
| Name | Type | Req | Description |
|---|---|---|---|
| dimensions | – | – | Custom embedding dimensions (model-dependent) |
| encoding_format | – | – | Output format: "float" or "base64" (default: float) |
| input | – | yes | Text string or list of strings to embed |
| model | – | – | Embedding model (e.g., "mistralai/mistral-embed-2312"). If not specified, uses DEFAULT_EMBEDDING_MODEL environment variable. |
Structured output declared, but exposes no named fields.
No examples provided.
find_models ~46
Search for models by name or slug.
| Name | Type | Req | Description |
|---|---|---|---|
| search_term | string | yes | Text to search for in model names (e.g., "claude", "gpt", "gemini") |
| Name | Type | Req | Description |
|---|---|---|---|
| result | array | yes | – |
No examples provided.
generate_image ~221
Generate an image using an OpenRouter image generation model.
| Name | Type | Req | Description |
|---|---|---|---|
| aspect_ratio | string | – | Aspect ratio - 1:1, 16:9, 9:16, 4:3, 3:4, or 21:9 |
| background | – | – | Background setting (e.g., "transparent" for PNG/WebP) |
| model | – | – | Image model (e.g., "google/gemini-3-pro-image-preview"). If not specified, uses DEFAULT_IMAGE_MODEL environment variable. |
| output_format | – | – | Output format (e.g., "png", "webp", "jpeg") |
| output_path | – | – | Optional absolute file path to save the image. Must be an absolute path if provided (e.g., "/Users/name/output.png"). |
| prompt | string | yes | Image description - be specific about style, colors, composition |
| quality | – | – | Quality setting (e.g., "high", "medium", "low") |
| size | string | – | Image size - 1K, 2K, or 4K |
No output schema declared.
No examples provided.
list_models ~83
List available OpenRouter models, optionally filtered by capability.
| Name | Type | Req | Description |
|---|---|---|---|
| capability | – | – | Filter by capability: - "vision": Models that can analyze images - "image_gen": Models that can generate images - "embedding": Models that can generate embeddings - "tools": Models that support tool/… |
| Name | Type | Req | Description |
|---|---|---|---|
| result | array | yes | – |
No examples provided.
How do I install the OpenRouter MCP server?
OpenRouter runs locally as a PyPI package, launched with uvx mcp-openrouter. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
pypi · mcp-openrouter
claude mcp add tsilva-mcp-openrouter -- uvx mcp-openrouter
What is the OpenRouter MCP server?
OpenRouter is an MCP server listed in the public MCP registry as io.github.tsilva/mcp-openrouter. MCP server providing access to 300+ AI models via OpenRouter. This page covers its PyPI package (mcp-openrouter).
Is the OpenRouter MCP server safe to use?
OpenRouter scores 90 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 16 October 2026. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the OpenRouter MCP server expose?
OpenRouter exposes 5 tools: chat, generate_image, embed, list_models, find_models. Their descriptions and schemas cost roughly 792 tokens of context every time the server is loaded.
Is the OpenRouter MCP server still maintained?
OpenRouter is still listed as active in the MCP registry. We last reached this channel on 16 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the OpenRouter MCP server under?
OpenRouter declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.