Watchlist tracking
Reviewed for relevance and future tracking value.
MCP100 Assessment
Watchlist / Tracking
Why we’re tracking it
Follow-up value is specific to LLMintel model retirement and migration lookups: Do provider-parsed retirement dates preserve source dates and distinguish recommended replacements from compatibility guarantees?
Reviewed · Documentation review; complete setup workflow not independently tested
Best fit
Live model lifecycle/deprecation lookup to stop agents from shipping retired model IDs.
What we know
Read-only public catalog MCP normalized across major model providers. It checks whether a model is active/deprecated, lists retiring models and provides provider-named replacements or explicitly labeled fallback candidates.
Maintenance / activity evidence
- @llmintel/mcp 0.2.0 published 2026-07-28T03:16:14.695Z
Tracking evidence observed Oct 5, 2026. These dated signals do not establish current maintenance. Reviewed enrichment confidence: high.
Verification gaps / watch-outs
- Installation and comprehensive security have not been independently audited.
- Read-only public lifecycle catalog.
- Optional API key.
- Sensitive access: Model stack choices may reveal architecture but no secrets required
- Low authority; main risk is stale/incomplete lifecycle data.
Full authority, access and evidence limits are available in Review context and Access & risk.
All limitations / Review context
Do provider-parsed retirement dates preserve source dates and distinguish recommended replacements from compatibility guarantees?
The bounded review of the publisher's documented LLMintel model retirement and migration lookups and release notices identified no disclosed material condition preventing an accurately scoped public tracking entry. The resource's operational permissions remain uncertainty; this assessment does not certify installation safety.
- Low authority; main risk is stale/incomplete lifecycle data.
- Read-only public lifecycle catalog.
- Optional API key.
- Model identifiers/lookup queries go to LLMIntel; each result carries provider source.
- Sensitive access: Model stack choices may reveal architecture but no secrets required
- Installation, client compatibility and comprehensive security have not been independently audited. Authentication and access depend on the configured services.
- Runtime behavior, dependencies and undisclosed vulnerabilities were not independently audited.
- Documented tool authority and any remote data handling must be checked before installation or use.
- Tool inventory, client matrix and permissions completeness were not requirements for this Radar tracking review.
- Not every model is tracked; unknown must not be treated as safe.
- Catalog/network failure is an error, never an OK verdict.
- Provider pages remain the ultimate source and can change.
Original activity observations
- @llmintel/mcp 0.2.0 published 2026-07-28T03:16:14.695Z
Technical identity
npm/@llmintel/mcp- Exact implementation source
- https://www.npmjs.com/package/@llmintel/mcp ↗
- Reviewed resource type
- MCP Server
- Repository identity
- hivemindunit/llmintel-mcp
- Package identity
- npm:@llmintel/mcp
- Service endpoint
- https://llmintel.ai/v1/mcp
Evidence & Sources
- Evidence basis
- Recorded source evidence
- Setup runtime verification
- Not independently runtime-tested by MCP100 for this setup workflow.
Reviewed · Latest source observation
- Package registry ↗
@llmintel/mcp
Recorded package identity, distribution or download evidence.
Includes references whose attribution is not established.
Setup · Watchlist
Install & Agents
Publisher instructions.
Source evidence observed .
Additional setup details required — see the specific gaps below.
Install / connect
Publisher instructionsPublic lifecycle catalog, optional LLMINTEL_API_KEY increases rate limit; publisher also documents hosted URL.
publisher install or stdio launch · Claude Code only · Publisher instructions
claude mcp add llmintel -- npx -y @llmintel/mcpConfigure / authenticate
MCP100 setup guideKeyless published lifecycle reads can use local npx or remote https://llmintel.ai/v1/mcp; LLMINTEL_API_KEY only increases request limit. Never imply source model deprecation data is real-time guaranteed.
Check connection
Suggested checkFor local `npx -y @llmintel/mcp` use MCP client tool discovery; for hosted catalog route list documentation tools. No external account credential required in documented keyless route.
Remove / uninstall / revoke
MCP100 setup guideIf you added this integration to Claude Code under the registration name `llmintel`, run `claude mcp remove llmintel` to unregister that client entry. In Claude Desktop, Cursor, VS Code or another host, delete/disable the corresponding named MCP registration in that host's settings and restart/reconnect. If you installed an npm package globally or operate a separate HTTP server, uninstall/stop it with its original deployment method. This does not delete user data or revoke service credentials.
MCP client unregister, stopping hosted processes, package uninstall, OAuth disconnect and token revocation are distinct actions.
A claude mcp remove command is only valid for Claude Code when the local registration actually has that name. Other MCP hosts require their own UI/config cleanup.
Separate credential guidance / limitations: Not applicable to the published keyless catalog connection.
Remove client registration · Claude Code only · MCP100 composed guide
claude mcp remove llmintel
Official Documentation & Sources
What it does
Read-only public catalog MCP normalized across major model providers. It checks whether a model is active/deprecated, lists retiring models and provides provider-named replacements or explicitly labeled fallback candidates.
- Capability
- Developer Tools
- Resource type
- MCP Server
- Best fit
- Live model lifecycle/deprecation lookup to stop agents from shipping retired model IDs.
Representative uses
- Check model lifecycle status
- List upcoming/past retirements
- Suggest provider-recommended replacement
- Audit source provenance
Limitations
- Not every model is tracked; unknown must not be treated as safe.
- Catalog/network failure is an error, never an OK verdict.
- Provider pages remain the ultimate source and can change.
Reviewed access
Access & risk
Review the exact access boundary before connecting this MCP to accounts, credentials, or sensitive data.
- Authentication
- Optional API key.
- Permissions
- Read-only public lifecycle catalog.
- Data handling
- Model identifiers/lookup queries go to LLMIntel; each result carries provider source.
- Cost
- free_or_keyed_rate_limit
- Risk and cautions
- Low authority; main risk is stale/incomplete lifecycle data.
Access scope and cautions
- Write actions
- None in the reviewed inventory
- Sensitive access
- Model stack choices may reveal architecture but no secrets required
- Risk level
- low
FAQ
Based on reviewed evidence as of 2026-10-08. Watchlist tracking is not a recommendation or a security certification.