ResolveMesh Compatibility Intelligence
RemoteAbout ResolveMesh Compatibility Intelligence
ResolveMesh Compatibility Intelligence is a hosted, read-only MCP server for AI agent builders. It provides source-backed lookups and dated compatibility changes with explicit evidence levels.
Key features
- 01Compatibility lookups for client-tool pairs
- 02Dated compatibility change events
- 03Evidence levels with primary-source citations
- 04Unauthenticated Streamable HTTP endpoint
Use cases
- 01Check whether a hosted tool works with an AI client
- 02Review sourced changes to compatibility over time
MCP support
The hosted MCP server exposes `compatibility_lookup` and `compatibility_changes` to MCP clients over Streamable HTTP at `https://resolvemesh.com/mcp/public`.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://resolvemesh.com/mcp/publicclaude mcp add --transport http resolvemesh https://resolvemesh.com/mcp/public{"mcpServers":{"resolvemesh":{"type":"http","url":"https://resolvemesh.com/mcp/public"}}}Open in Cursor{"servers":{"resolvemesh":{"type":"http","url":"https://resolvemesh.com/mcp/public"}}}Open in VS Code{"mcpServers":{"resolvemesh":{"type":"http","url":"https://resolvemesh.com/mcp/public"}}}{"mcpServers":{"resolvemesh":{"serverUrl":"https://resolvemesh.com/mcp/public"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
2| Parameter | Type | Required | Description |
|---|---|---|---|
| client | enum | Yes | chatgpt-web | chatgpt-desktop | claude-code | cursor | codex | gemini-cli | vs-code | windsurf | copilot-coding-agent |
| tool | enum | Yes | github | linear | figma | notion | atlassian | stripe | supabase | sentry | vercel | neon |
Details
From the project READMEResolveMesh Compatibility Intelligence — hosted MCP server
Listing repository for the hosted, read-only ResolveMesh compatibility MCP server. The service code is not in this repository; this repo exists so directories that index GitHub can reference the hosted endpoint.
- Endpoint (Streamable HTTP):
https://resolvemesh.com/mcp/public - Official MCP Registry record:
com.resolvemesh/compatibility - Website: https://resolvemesh.com — compatibility matrix, reviewed change ledger, and field guides for AI agent builders
Tools
| Tool | What it returns |
|---|---|
compatibility_lookup | The source-backed compatibility result for one allowlisted AI-client / hosted-tool pair (7 clients × 5 tools) |
compatibility_changes | Approved, dated compatibility change events with official sources, filterable by client, tool, severity, and time |
Answers carry explicit evidence levels (DOCUMENTED, LIKELY_COMPATIBLE,
CONDITIONAL, UNSUPPORTED, UNKNOWN) and cite primary sources. Inference
is never presented as a tested integration. The endpoint requires no
authentication, sets no cookies, and stores no user data.
Use it
{
"mcpServers": {
"resolvemesh-compatibility": {
"url": "https://resolvemesh.com/mcp/public"
}
}
}
REST equivalents: /v1/compatibility
and /v1/compatibility-changes.
RSS: /changes/feed.xml.
Machine map: /llms.txt.
TypeScript SDK
The typed client for the authenticated ResolveMesh REST API is published as
@resolvemesh/sdk:
npm install @resolvemesh/sdk
import { createResolveClient } from "@resolvemesh/sdk";
The SDK targets the authenticated resolution and outcome endpoints (bearer API key required — pilot access is founder-approved). The compatibility MCP endpoint above needs no SDK and no key.
License
MIT — applies to this listing repository only.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.