Developer · Local MCP server
Modelwatch
Continuous behavioral drift monitoring for LLM apps - catches silent provider model updates.
What the MCP Registry states
The entry as published to the official MCP Registry (read 2026-10-04), latest version.
- Registry name
io.github.bch1212/modelwatch- Version
- 0.1.2
- Status
- Active
- Category
- developer
- Transport
- stdio (local process)
- Package
- npm
- Published
- 2026-10-01
- Updated
- 2026-10-01
- Publisher
- bch1212 (GitHub) · 11 servers with pages here
- Namespace
- Namespace verified by the MCP Registry via GitHub (github.com/bch1212) · how
- Website
- modelwatch.app
- Repository
- github.com/bch1212/modelwatch (folder mcp-server)
- Source
- Registry API entry
Packages
| Registry | Package | Version | Transport |
|---|---|---|---|
| npm | modelwatch-mcp | 0.1.2 | stdio |
How to connect Modelwatch
Modelwatch runs locally from a Node.js package published to the npm registry: modelwatch-mcp version 0.1.2. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Node.js; clients usually start it with npx - the usual command is npx -y modelwatch-mcp@0.1.2. It reads these environment variables: MODELWATCH_API_KEY (required, secret) and MODELWATCH_API_BASE; set them in the client's configuration for this server.
In the mcpServers JSON format that many desktop and editor MCP clients read, the entry looks like this (placeholders in angle brackets):
{
"mcpServers": {
"modelwatch": {
"command": "npx",
"args": [
"-y",
"modelwatch-mcp@0.1.2"
],
"env": {
"MODELWATCH_API_KEY": "<secret>",
"MODELWATCH_API_BASE": "<value>"
}
}
}
}Derived from the registry entry, not tested here. What the server does, and on what terms, is set by its publisher; check its repository or website before giving it access to your accounts or files. How to add an MCP server to an assistant · Before you connect
More from bch1212 (GitHub)
| Server | Runs |
|---|---|
| Agent Commerce MCPAgent Commerce MCP - agent-native A2A storefront. Discovery, Stripe checkout, affiliate program. | Remote & Local · HTTP, stdioLive check: ✓ handshake |
| AgentfetchToken-budgeted web fetch for AI agents - auto-routes Jina, FireCrawl, Trafilatura, PDF. | Local · stdio |
| AgenttrustTrust scores & reputation for the agent-to-agent economy. Verify A2A counterparties. | Local · stdio |
| AgentvaultCredential vault for AI agents - Fernet-encrypted keys, per-agent budgets, audit logs. | Local · stdio |
| BizintelLocal business intel for AI agents: audits, lead scoring, tech stack, prospecting. | Remote · HTTPLive check: ✓ handshake |
| InjectshieldPrompt-injection firewall for AI agents - scan untrusted text before LLM calls. | Local · stdio |
| MCP GrantiqSearch US grants + federal contracts (Grants.gov + SAM.gov) from any LLM. | Remote · HTTPLive check: ✓ handshake |
| Outdooriq MCPPaid MCP for fishing/lake/stocking intelligence - 72k+ US lakes, 293k+ events. | Remote · HTTPLive check: sign-in required |
| PubrecordsUS public-records intelligence for AI agents - companies, SEC, courts, spending, licenses. | Remote · HTTPLive check: ✓ handshake |
| QueryshieldSecure SQL proxy for AI agents - NL→SQL, AST safety, per-agent RLS, audit log. | Local · stdio |
More developer servers
| Server | Runs |
|---|---|
| Model Price RadarLLM prices on OpenRouter now and since 2023: history, drops, cheapest model for a job. No API keys. | Local · stdio |
| Modelbound MCPLocal-first MCP server for agent skills. Validate, lint, diff, and convert across IDEs. | Local · stdio |
| ModelcostsaverOffline MCP: predict LLM call cost and pick the cheapest capable model. No keys, no network. | Local · stdio |
| modelpricewatch.comLive LLM API pricing: token prices, comparisons, cheapest-model lookups. No key required. | Remote & Local · HTTP, stdioLive check: ✓ handshake |
| MojuloA 3D compiler for coding agents: objects, worlds and games as small recipes. Emits Godot and STL. | Local · stdio |
| Moltalyzer MCPPolymarket prediction-market intelligence + AI, GitHub & narrative feeds for agents, via x402. | Local · stdio |
| MoltArchMarketing intelligence API for AI agents. Real campaign data, not LLM guesses. | Remote · HTTPLive check: ✗ no handshake |
| Moltline Code ReviewRisk-scan a diff, flag AI-generated-code tells, find secrets. 5 of 7 tools need no account. | Remote · HTTPLive check: ✓ handshake |