ModelRouter
FreeNot checkedAdvisory MCP server for intelligent LLM model recommendations in Cursor. Provides tools for task analysis, repository analysis, and model selection guidance.
About
Advisory MCP server for intelligent LLM model recommendations in Cursor. Provides tools for task analysis, repository analysis, and model selection guidance.
README
Advisory MCP server for intelligent LLM model recommendations in Cursor.
v1 Capability Statement
Ships:
- Advisory
recommend_modelwith schema-validated JSON - Heuristic task analysis (Layer A) + metadata scoring (Layer B)
- Static seed registry with user-writable cache (
~/.modelrouter) - Live metadata sync by default (Class D inbound fetch when
privacyMode: false) - Guidance snippets for Cursor — user manually picks model
Does NOT ship:
- Force Composer/Auto model selection
- Continuous validation against engineering tasks (Phase 8 opt-in only)
Cursor.models.list()or any IDE runtime model API
Quick Start
npm install
npm run build
MODELROUTER_USE_FIXTURES=1 npm test
npm run validate-schemas
npm run smoke
Cursor MCP Configuration
npm (after publish):
{
"mcpServers": {
"modelrouter": {
"command": "npx",
"args": ["-y", "modelrouter-mcp"]
}
}
}
Local development:
{
"mcpServers": {
"modelrouter": {
"command": "node",
"args": ["/absolute/path/to/ModelRouter_MCP/dist/index.js"]
}
}
}
Tools (10)
| Tool | Description |
|---|---|
recommend_model |
Advisory recommendation from plan + repo metadata |
analyze_task |
Task type, complexity, requirement vector |
analyze_repository |
File counts, languages, frameworks, diff stats |
list_models |
Registry model list |
get_model_profile |
Full profile with provenance |
sync_metadata |
Sync from external sources (blocked in privacy mode) |
generate_cursor_guidance |
Advisory snippets — does not apply model |
get_telemetry_summary |
Local telemetry only |
estimate_cost |
Cost estimate for a specific model |
run_internal_validation |
Opt-in stub validation (disabled by default) |
Benchmark ingest is internal-only (via SweBenchAdapter), not exposed as an MCP tool.
Configuration
See schemas/modelrouter-config.schema.json.
| Setting | Default | Notes |
|---|---|---|
privacyMode |
false |
Blocks all outbound HTTP when true |
sync.enabled |
true |
Disable to skip metadata sync |
sync.sources |
all adapters | Filter by source ID |
validation.enabled |
false |
Opt-in; may incur API costs |
Environment variables (not in JSON schema):
MODELROUTER_DATA_DIR— override user cache directory (default~/.modelrouter)MODELROUTER_USE_FIXTURES=1— fixtures only, no live HTTP (CI/dev offline)
Privacy
See PRIVACY.md. User plan and repository data are never sent outbound. Optional public model metadata fetch (Class D) occurs when privacyMode: false.
Data directories
| Path | Purpose |
|---|---|
Packaged data/models/ |
Read-only seeds (npm install) |
~/.modelrouter/models/ |
Writable user cache (sync updates) |
~/.modelrouter/sync-state.json |
Last sync TTL tracking |
Single-instance assumption: concurrent writes are not supported.
Troubleshooting
- Build errors: Run
npm run buildbefore starting MCP - Stale metadata: Call
sync_metadataor wait for background TTL sync (24h) - Offline dev: Set
MODELROUTER_USE_FIXTURES=1 - Privacy: Set
privacyMode: truein config to block all outbound HTTP
Maintainer Scripts
# Optional — requires CURSOR_API_KEY
npm run verify-cursor-ids
# CI denylist check
npm run lint:cursor-denylist
# Record live sync fixtures (network required)
npx tsx scripts/record-sync-fixtures.ts
Implementation status
| Phase | Status |
|---|---|
| Runtime foundation (user dir, async sync) | Complete |
| Live metadata sync | Complete |
| Registry quality (cursor IDs, benchmarks) | Complete |
| Calibration | Provisional (run npx tsx scripts/calibrate-scoring.ts to validate) |
| npm publish | Ready |
See CONTRIBUTING.md for maintainer workflows.
License
MIT — see LICENSE
Install ModelRouter in Claude Desktop, Claude Code & Cursor
unyly install modelrouter-mcpInstalls into Claude Desktop, Claude Code, Cursor & VS Code — handles npx, uvx and build-from-source repos for you.
First time? Get the CLI: curl -fsSL https://unyly.org/install | sh
Or configure manually
Run in your terminal:
claude mcp add modelrouter-mcp -- npx -y github:MrSolution07/ModelRouter_MCPFAQ
Is ModelRouter MCP free?
Yes, ModelRouter MCP is free — one-click install via Unyly at no cost.
Does ModelRouter need an API key?
No, ModelRouter runs without API keys or environment variables.
Is ModelRouter hosted or self-hosted?
Self-hosted: the server runs locally on your machine via the install command above.
How do I install ModelRouter in Claude Desktop, Claude Code or Cursor?
Open ModelRouter on unyly.org, pick your client tab (Claude Desktop, Claude Code, Cursor) and press Install — the config is generated automatically, no JSON editing.
Related MCPs
Notion
Read and write pages in your workspace
by NotionLinear
Issues, cycles, triage — from Claude
by LinearGoogle Drive
Search and read your Drive files
by Googlemindsdb/mindsdb
Connect and unify data across various platforms and databases with [MindsDB as a single MCP server](https://docs.mindsdb.com/mcp/overview).
by mindsdbCompare ModelRouter with
Not sure what to pick?
Find your stack in 60 seconds
Author?
Embed badge for your README
Browse similar
All productivity MCPs
