Server data from the Official MCP Registry
Competitive intelligence — track what competitors ship each week. 8 tools, 3 prompt workflows.
Competitive intelligence — track what competitors ship each week. 8 tools, 3 prompt workflows.
Remote endpoints: streamable-http: https://mcp.meertrack.com/mcp
Well-structured MCP server with proper authentication, no malicious patterns, and appropriate permission scoping. The server correctly validates all inputs via Zod schemas, handles errors safely, and uses environment variables for secrets. Minor code quality observations around broad error handling and non-sensitive logging practices do not materially affect security. Supply chain analysis found 12 known vulnerabilities in dependencies (1 critical, 4 high severity). Package verification found 1 issue.
5 files analyzed · 17 issues found
Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.
This plugin requests these system permissions. Most are normal for its category.
Set these up before or after installing:
Environment variable: MEERTRACK_API_KEY
Environment variable: MEERTRACK_API_BASE_URL
Available as Local & Remote
This plugin can run on your machine or connect to a hosted endpoint. during install.
From the project's GitHub README.
@meertrack/mcpModel Context Protocol server for Meertrack. Ask your agent "what did my competitors ship this week?" from Claude, Cursor, Claude Code, VS Code, Windsurf, Cline, ChatGPT, or anywhere that speaks MCP.
Wraps the Meertrack v1 REST API as 8
read-only tools and 3 prompt workflows. No backend changes, same
mt_live_ keys, same rate limits.
| Local (stdio) | Remote (Streamable HTTP) | |
|---|---|---|
| Setup time | 30 seconds (paste a JSON block) | 10 seconds (paste a URL) |
| Best for | Individual Pro customers; all Claude Desktop plans; any IDE on your laptop | Team/Enterprise custom connectors; Claude.ai web; remote-capable IDEs |
| Runs where | Your machine (npx -y @meertrack/mcp) | Meertrack's Fly.io fleet (https://mcp.meertrack.com/mcp) |
| Auth | MEERTRACK_API_KEY env var | Authorization: Bearer mt_live_… header |
| Plan gating | Works on Claude Pro, Team, Enterprise | Claude Desktop "Add custom connector" is Team/Enterprise only |
If you're on Claude Pro, use the local (stdio) path. The "Add custom
connector" button in the Claude Desktop settings is gated to Team/Enterprise,
and pasting https://mcp.meertrack.com/mcp there won't do anything on a Pro
plan.
Mint a production key at Settings → API Keys in the Meertrack app. Keys
start with mt_live_. Only production keys work; there is no mt_test_
flavour.
Rate limits. Each API key shares a 60 requests/minute budget enforced upstream. If you run the MCP from multiple clients at once (Claude Desktop + Cursor + a background agent) they all draw from the same bucket. Mint a separate key per workstation or per agent to isolate budgets. The tool-error message on 429 includes both a human-readable reset time and the raw
X-RateLimit-Resetepoch so the agent can back off automatically.
All local-mode clients use the same shape: npx -y @meertrack/mcp with
MEERTRACK_API_KEY in the environment. What differs is the config file and
the surrounding JSON key.
Drop-in copies of every config file below live in examples/.
Edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS)
or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"meertrack": {
"command": "npx",
"args": ["-y", "@meertrack/mcp"],
"env": {
"MEERTRACK_API_KEY": "mt_live_..."
}
}
}
}
Gotcha: Claude Desktop only re-reads this file on launch. Fully quit (⌘Q on macOS) and reopen. Reloading the window is not enough.
Edit ~/.cursor/mcp.json (or .cursor/mcp.json in a project):
{
"mcpServers": {
"meertrack": {
"command": "npx",
"args": ["-y", "@meertrack/mcp"],
"env": {
"MEERTRACK_API_KEY": "mt_live_..."
}
}
}
}
claude mcp add meertrack npx -y @meertrack/mcp \
--env MEERTRACK_API_KEY=mt_live_...
Edit .vscode/mcp.json (per-workspace) or the user settings equivalent:
{
"servers": {
"meertrack": {
"command": "npx",
"args": ["-y", "@meertrack/mcp"],
"env": {
"MEERTRACK_API_KEY": "mt_live_..."
}
}
}
}
Gotcha: VS Code uses
servers, notmcpServers. The Copilot MCP picker won't find your server if you use the Claude Desktop key.
Edit ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"meertrack": {
"command": "npx",
"args": ["-y", "@meertrack/mcp"],
"env": {
"MEERTRACK_API_KEY": "mt_live_..."
}
}
}
}
Gotcha: Windsurf's remote-connector shape uses
serverUrl, noturl. For the stdio config above, the shape is identical to Claude Desktop.
Cline's settings panel → "MCP Servers" → paste:
{
"mcpServers": {
"meertrack": {
"command": "npx",
"args": ["-y", "@meertrack/mcp"],
"env": {
"MEERTRACK_API_KEY": "mt_live_..."
},
"disabled": false,
"autoApprove": []
}
}
}
All remote clients point at the same URL:
https://mcp.meertrack.com/mcp
...with Authorization: Bearer mt_live_…. One shared hosted server. Nothing
to install locally.
Settings → Connectors → Add custom connector → paste the URL above and your bearer token when prompted. The "Add custom connector" button is not visible on Pro; use the stdio path above instead.
Same as above in the web app's Connectors panel.
{
"mcpServers": {
"meertrack": {
"url": "https://mcp.meertrack.com/mcp",
"headers": {
"Authorization": "Bearer mt_live_..."
}
}
}
}
Paste the URL and bearer in the ChatGPT "Add MCP" dialog. Note: ChatGPT's bearer support is minimal today; full OAuth parity is tracked as Phase 11.
https://mcp.meertrack.com/mcpPOSTAuthorization: Bearer mt_live_…, Accept: application/json, text/event-stream, MCP-Protocol-Version: 2025-11-25All read-only, all snake_case. Collection returns use the list_ prefix;
single-item returns use get_. Every list response includes
pagination.next_cursor and pagination.has_more, and agents must pass
next_cursor back as cursor to fetch the next page.
| Domain | Tool | Wraps | Notes |
|---|---|---|---|
| Identity | whoami | GET /me | Confirms workspace + subscription + rate-limit snapshot. Call first. |
| Competitors | list_competitors | GET /competitors | Defaults to expand=full so agents don't round-trip for socials/pages. |
| Competitors | get_competitor | GET /competitors/{id} | 11 tracked sections (blog, pricing, jobs, …) with per-section caps. |
| Activity | list_activities | GET /activity | Core "what shipped" feed. Default limit=50 to stay under tool-result size limits. |
| Activity | get_activity_item | GET /activity/{row_uuid} | Drill-in for a specific row's full payload. |
| Digests | list_digests | GET /digests | Cursor-paginated weekly digests. No total field (unlike activity). |
| Digests | list_latest_digests | GET /digests/latest | No params; one-shot "what happened this week". |
| Digests | get_digest | GET /digests/{id} | Full summary + themes for one competitor × period. |
Full input / output / error-code documentation is on the tool descriptions themselves, and the MCP client displays them inline.
Slash commands in Claude Desktop / Cursor / Claude Code / any prompt-capable MCP client. Each one chains tool calls into a complete workflow.
| Prompt | Args | Chains |
|---|---|---|
/weekly_recap | none | list_latest_digests → per-competitor summary + highlights |
/competitor_deep_dive | competitor_name | list_competitors → get_competitor → list_activities (last 30d) |
/whats_new | days? (default 7) | list_activities from now - N days, grouped by competitor |
/weekly_recap/competitor_deep_dive competitor_name="Acme"/whats_new days="14"See examples/prompts.md for a dozen copy-paste user
prompts grouped by use case (weekly check-in, feature spec research, pricing
comparison, board-deck prep).
When the upstream API returns an error, the MCP tool response surfaces the
upstream code in the error text. Map them:
Upstream code | What it means | Fix |
|---|---|---|
unauthorized | Key is invalid, revoked, or expired | Mint a new key at Settings → API Keys and update the config |
competitor_inactive | Competitor is archived in this workspace | Reactivate the competitor in the dashboard |
forbidden_competitor | The id you passed isn't in this workspace | Call list_competitors first to discover valid ids |
rate_limited | 60 req/min cap hit | Wait until the reset timestamp in the error message, or mint a second key for the other client |
not_found | No such row in this workspace | The id is either wrong or belongs to a different workspace |
invalid_parameter / invalid_cursor | Bad input | Check the error message; cursors expire, so re-list from the start |
Other common snags
command not found: npx → install Node ≥ 20. The MCP pins engines.node.WWW-Authenticate: Bearer → your bearer is
missing, malformed, or doesn't start with mt_live_.Authorization header.MCP tool schemas are part of the public API contract; agents cache them. So:
See CHANGELOG.md for the release history.
security@meertrack.com),
in-scope surface.MIT.
Be the first to review this server!
by Modelcontextprotocol · Developer Tools
Read, search, and manipulate Git repositories programmatically
by Toleno · Developer Tools
Toleno Network MCP Server — Manage your Toleno mining account with Claude AI using natural language.
by mcp-marketplace · Developer Tools
Create, build, and publish Python MCP servers to PyPI — conversationally.
by Microsoft · Content & Media
Convert files (PDF, Word, Excel, images, audio) to Markdown for LLM consumption
by mcp-marketplace · Developer Tools
Scaffold, build, and publish TypeScript MCP servers to npm — conversationally
by mcp-marketplace · Finance
Free stock data and market news for any MCP-compatible AI assistant.