meetmyagentSAFE
Retired: MCP client for MeetMyAgent's former listing catalog. Today: connect the hosted server https://meetmyagent.io/mcp to run your business's AI agent.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Part of the [StudioMeyer MCP Stack](https://studiomeyer.io) · Built in Mallorca 🌴 · ⭐ if you use it
[](https://www.npmjs.com/package/meetmyagent-mcp) [](https://www.npmjs.com/package/meetmyagent-mcp)
[!IMPORTANT] This package is retired. It was a client for MeetMyAgent's former listing catalog, which is no longer part of the product. MeetMyAgent today gives every business its own AI agent: it answers customer questions around the clock, on the business's website and on its own page, and passes requests on to the owner. To set up and run your agent from Claude, ChatGPT, Cursor or Codex, connect the hosted MCP server at https://meetmyagent.io/mcp (OAuth sign-in). The current REST API is described at meetmyagent.io/v1. The code below stays as a reference implementation. Its catalog tools no longer have an API behind them.Former purpose (reference): put the MeetMyAgent catalog inside your AI. Claude, Cursor, Codex or ChatGPT can search the listing catalog and, with your own API key, put a business, service or product into it.
Reads are anonymous and zero-config: no account, no key needed to search, read listings
2ea8575db4a0OBSERVED · 2026-10-11Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add meetmyagent-mcp -- npx -y [email protected]
{
"mcpServers": {
"meetmyagent-mcp": {
"command": "npx",
"args": [
"-y",
"[email protected]"
]
}
}
}Exposed tools (10)
7 read · 3 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
mma_create_listing | write | List a business, service or product on MeetMyAgent (free, facet-validated). Call mma_describe_catalog first and use ONLY its facet keys + enum values in |
mma_describe_catalog | read | Read the self-describing facet schema BEFORE searching or listing. Without a category it lists all categories (with live counts); with a category it returns that category |
mma_get_blog | write | Read the MeetMyAgent blog: a slug returns one post (as |
mma_get_listing | read | Fetch one listing by id — full detail incl. the agent/provider behind it, the verified-business badge, and next-action |
mma_get_provider | read | The public profile of a provider (the |
mma_guide | read | ALWAYS call this first when a user connects or asks what MeetMyAgent is. Returns the live agent operator manual (invariants, the uniform response envelope, the search/list/deal flows, webhooks, error recovery). Read it back to the user, then help them list or find something. |
mma_import_listing | write | Zero-form listing: import a draft from a URL or pasted text (quarantined extraction). Returns a draft + a gapReport of what is still missing; fill the gaps, then publish from the console. Needs an API key with the listings:write scope. |
mma_list_requests | read | Browse the demand side — things people are actively looking for. Filter by status, category or tag. Answer one by pointing the user to https://meetmyagent.io/en/requests. |
mma_my_listings | read | List the listings under your own account (needs your API key). |
mma_search | read | Structured catalog search: a category + facet filters, an optional natural-language |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (3 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (1)
@modelcontextprotocol/sdk, @types/node, tsx, typescript
Gates applied: no_behavioural_pass.
2ea8575db4a0full audit observations/trust-audit/mcp-server/studiomeyer-io__meetmyagent-mcp.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-11 | 2ea8575db4a0 | SAFE | B | 89 | first audit |
Questions
What is the meetmyagent MCP server?
Retired: MCP client for MeetMyAgent's former listing catalog. Today: connect the hosted server https://meetmyagent.io/mcp to run your business's AI agent.
What tools does meetmyagent expose?
10 in total: 7 read-only, 3 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is meetmyagent safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does meetmyagent need?
No credential environment variables were found in its source, so it appears to need none.
How does meetmyagent run?
It speaks stdio and streamable-http, so it runs as a local process your client starts. It is published on npm as meetmyagent-mcp at 0.2.0.
How current is this page?
The grade is for one exact copy of the source (2ea8575db4a0), read on 2026-10-11. The repository is watched and re-audited when it changes.