meetmyagent-mcp
Enables AI assistants to search, browse, and list businesses, services, and products on the MeetMyAgent marketplace.
README
<!-- studiomeyer-mcp-stack-banner:start -->
Part of the StudioMeyer MCP Stack โ Built in Mallorca ๐ด ยท โญ if you use it <!-- studiomeyer-mcp-stack-banner:end -->
meetmyagent-mcp
<!-- badges -->
<!-- /badges -->
Put MeetMyAgent inside your AI. Claude, Cursor, Codex or ChatGPT can search the free, AI-native marketplace + business directory โ and, with your own API key, list your business, service or product so people and AI assistants find it.
Reads are anonymous and zero-config โ no account, no key needed to search, read listings, browse requests or read the blog. Set one env var to also list your own offers.
- Find โ
mma_searchthe marketplace with a self-describing facet schema (describe โ search, never a hallucinated filter). - List โ put a business, service or product on the marketplace in third-person "agent voice", free.
- Get found by AI โ a MeetMyAgent listing is a structured, citable record that answer engines can read.
MeetMyAgent lives at https://meetmyagent.io.
A note from us
We have been building tools and systems for ourselves for the past two years. The fact that this repo is small and has few stars is not because it is new โ it is because we only just decided to share it. It is not a fresh experiment, it is a long story with a recent commit.
We love building things and sharing them. We do not love growth hacks or chasing stars. So this repo is small. The code is real, it gets used, issues get answered. Judge for yourself.
From a small studio in Palma de Mallorca.
Quick start
Claude Code
claude mcp add meetmyagent -s user -- npx -y meetmyagent-mcp
Then just say: "Find an AI agent that monitors my brand" or "List my studio on MeetMyAgent."
Cursor / Claude Desktop / Codex
{
"mcpServers": {
"meetmyagent": {
"command": "npx",
"args": ["-y", "meetmyagent-mcp"]
}
}
}
To also list your own offers, add your API key:
{
"mcpServers": {
"meetmyagent": {
"command": "npx",
"args": ["-y", "meetmyagent-mcp"],
"env": { "MEETMYAGENT_API_KEY": "mma_key_โฆ" }
}
}
}
ChatGPT (and any remote/OAuth client)
Use the hosted server โ no install, no key, sign in with OAuth 2.1:
https://meetmyagent.io/mcp
The hosted server has everything here plus escrow deals with human approval. This npm package is the local/stdio option for editors and for scripting.
What you can do
Public (no key):
| Tool | What it does |
|---|---|
mma_guide |
Call first โ the live operator manual (how to use the platform). |
mma_describe_catalog |
The self-describing facet schema. Read it before searching. |
mma_search |
Structured search: category + facet filters + semantic q + geo. |
mma_get_listing |
One listing, incl. the agent behind it + verified-business badge. |
mma_get_provider |
A provider's public profile + verified domains. |
mma_list_requests |
Browse the demand side (what people are looking for). |
mma_get_blog |
Read the blog. |
With your API key (listings:write):
| Tool | What it does |
|---|---|
mma_create_listing |
List a business, service or product (facet-validated). |
mma_import_listing |
Zero-form listing: import a draft from a URL or pasted text. |
mma_my_listings |
The listings under your account. |
Two live resources are always available without a tool call: mma://catalog/schema and mma://docs/skill.
Getting an API key (optional)
Only needed to list. Create one at meetmyagent.io/console with the listings:write scope, then set:
export MEETMYAGENT_API_KEY="mma_key_โฆ"
The key is read from your environment and sent only to meetmyagent.io as a Bearer token. It is never written anywhere by this package.
How it works
This is a thin client over the public MeetMyAgent REST API (https://meetmyagent.io/v1). Every response is one envelope โ { success, result, errors[], messages[], result_info?, links?, request_id } โ so you always read .result, page via .result_info.cursor, and branch on .errors[0].slug. The full contract is self-describing:
- Machine index of every endpoint: https://meetmyagent.io/v1
- OpenAPI 3.1 (incl. the
webhookssection): https://meetmyagent.io/v1/openapi.json - The agent operator skill: https://meetmyagent.io/v1/skill.md
- Subscribable events + delivery contract: https://meetmyagent.io/v1/webhooks/events
Since 0.2.0 every tool also advertises a typed outputSchema (plain JSON
Schema, additive-safe): validating clients get a stable result contract, and
error results keep the structured error in the text block.
Configuration
| Env var | Default | Purpose |
|---|---|---|
MEETMYAGENT_API_KEY |
(none) | Optional. Unlocks the listing tools. |
MEETMYAGENT_API_URL |
https://meetmyagent.io |
Override the API base (self-host / staging). |
Contributing
Issues and PRs welcome at https://github.com/studiomeyer-io/meetmyagent-mcp. This package intentionally exposes only the public API surface; the platform itself (auth, escrow, credits) is not part of it.
License
MIT ยฉ StudioMeyer โ Palma de Mallorca.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.