# modelwatch-mcp

MCP server for ModelWatch — continuous behavioral drift monitoring for LLM-powered applications.

- **Type:** MCP server
- **Trust:** 85/100 (A), scored on the package rubric
- **Verification:** verified (build provenance)
- **Version:** 0.1.3
- **Author:** io.github.bch1212
- **License:** MIT
- **npm:** modelwatch-mcp
- **Source:** https://github.com/bch1212/modelwatch
- **Compatible clients:** claude-code, cursor, copilot, gemini (basis: transport)

## Trust

85/100 (A), scored on the package rubric
- Publisher verified: no
- Build provenance: verified attestation
- npm trusted publishing (OIDC): yes
- Install scripts: nothing suspicious found
- Prompt-injection scan: not run
- Obfuscation scan: not run
- Evidence age: 0 days

## Security scan

- **Status:** clean
- **Scanned:** 2026-10-11T20:13:33.882Z
- **Version scanned:** 0.1.3
- **CVEs:** none found by OSV at scan time

## Tools

9 declared. Statically extracted from the shipped source — a floor on the surface, not a census.
- `list_endpoints` — List the LLM endpoints currently monitored in this workspace.
- `create_endpoint` — Register an LLM endpoint to monitor. The workspace must already have
- `list_specs` — List behavioral specs in the workspace. A spec is a stored prompt +
- `create_spec` — Create a behavioral spec. The first run after creation sets the
- `run_spec` — Run a spec on demand and return the drift score immediately. Use this
- `reset_baseline` — Clear a spec's baseline. The next run will record a new baseline
- `get_drift_events` — Fetch recent drift events across the workspace, newest first. Each
- `get_spec_history` — Get the run history for a single spec. Returns each run's status,
- `get_health` — Per-spec health across the workspace: spec_id, spec_name, endpoint_name,

## Install

**Verdict: install** — No blocking findings and no open coverage gaps — safe to install as configured.
**Config** (claude-code):
```json
"{\n  \"mcpServers\": {\n    \"modelwatch\": {\n      \"command\": \"npx\",\n      \"args\": [\n        \"-y\",\n        \"modelwatch-mcp\"\n      ],\n      \"env\": {\n        \"MODELWATCH_API_KEY\": \"<YOUR_MODELWATCH_API_KEY>\"\n      }\n    }\n  }\n}"
```
**Credentials it will ask for** (names only — Forge never holds a value):
- `MODELWATCH_API_KEY` — Modelwatch API Key (required)
Placeholders only. Forge never holds, brokers, or transmits a credential value — replace each <YOUR_NAME> in your own config file. Do not send a value back to Forge; no Forge endpoint accepts one.
- This entry needs 1 credential (1 required). The generated config carries placeholders, so it will fail in the editor rather than at runtime if they are left unset.

## Blast radius

Moderate blast radius — holds an api key; runs on your machine.
- Floor 23, ceiling 23 (tier: moderate)
- This is impact, not likelihood. A high radius is not a defect: a filesystem server is supposed to write files. It is never part of the trust score.

## Machine-readable views of this entry

- Signed JSON: https://forgeregistry.com/api/v1/packages/modelwatch-mcp
- Install plan: https://forgeregistry.com/api/v1/packages/modelwatch-mcp/install-plan
- Alternatives: https://forgeregistry.com/api/v1/alternatives/modelwatch-mcp
- HTML page: https://forgeregistry.com/registry/modelwatch-mcp
- MCP: POST https://forgeregistry.com/api/mcp → `forge_get_package` / `forge_install_plan`

## About this document

Generated by Forge (https://forgeregistry.com) — a compact rendering of the same record served, signed, at the JSON URL above. Trust and scan facts are the registry's own measurements; anything Forge did not measure is named as unmeasured rather than omitted.