Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@9router-mcp check pool headroom and list available models"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP server (stdio, newline-delimited JSON-RPC 2.0) for a local 9router LLM gateway. No dependencies; requires Bun.
router_models - live models, pool headroom and seven-day call statistics
router_headroom - pool capacity, cooldowns and in-flight calls
router_chat - chat with exactly one model; never silently switches models, suggests an alternative from the task rows on rate limit
router_probe - sequential eight-token probes
router_usage - read-only usage totals by key name
router_search / router_fetch - search and page fetch; paid Firecrawl needs allow_firecrawl: true
Related MCP server: io.github.0xzr/freellmpool
claude mcp add -s user 9router-mcp -- bun /absolute/path/to/9router-mcp/index.tsAdd -e NAME=value for any variable below.
ROUTER_BASE: router origin; default http://127.0.0.1:20128. Loopback 127.0.0.1 only.
ROUTER_CACHE: shared state directory (limits.json, calls.jsonl); default ~/.cache/pi-runs.
ROUTER_DB: router SQLite file; default ~/.9router/data.sqlite. Read-only.
ROUTER_HEADROOM_SCRIPT: executable run with --json; default model-headroom. Must print an array or {pools: [...]} of {pool, percent_left, status, reset_at}.
ROUTER_TASK_ROWS: path to a JSON file of fallback rows; default task-rows.json next to index.ts.
Task rows are ordered lists of model IDs from weakest to strongest:
[["glm/example-small"], ["cx/example-medium", "cx/example-large"]]When a model in a row is rate limited, the next healthy model in the same row is suggested as alternative.
Key redaction: values from the router apiKeys table, sk- strings, Bearer tokens and secret-named fields are replaced with [REDACTED] in all output and logs. Only key names are ever selected for usage.
Rate limits: per-pool concurrency caps, cooldowns from retry-after (or 5 minutes doubling to 60), a learned cap of N-1 after a 429, and a fusion-call cap.
Prompts are never logged; the router DB is never written; no authorization header is sent.
bun test <file>Run files one at a time. mutation.test.ts temporarily edits router.ts and restores it; run it alone.
Search/fetch are not covered by the shared limits.
Upstream body reads lack independent deadlines.
A crashed process can leave a lock needing manual removal.
This server cannot be deployed
OpenAI-compatible LLM gateway: pay per request with an API key, signed receipt for each call.
Gateway between LLM agents and world data through eight tools and a bundled endpoint catalog.
LLM cost optimization gateway, repo token-waste auditor & model arbitrage MCP server.
LLM cost optimization gateway, repo token-waste auditor & model arbitrage MCP server.
