# The GTM MCP Directory

> 293 GTM tools counted, 144 with an official MCP server. Which tools an agent can actually call, and which ones a solo operator can reach without a procurement cycle.

*Markdown twin of the HTML page at the same path. Same content, no navigation, no styling, no scripts. Links below point at other twins. Site map for machines: [llms.txt](llms.txt). The whole dataset: [directory.json](data/directory.json).*

---
**Agent Operator**

# The GTM MCP
Directory

Every GTM tool your agent can use, and which one does the job.

**293 tools** counted · **144 official MCP servers** · generated **2026-08-25** by build_directory.py (phase 1) · reconciled against tools_recount.py

- **tools counted**: 293

- **official MCP servers**: 144

- **community MCP**: 21

- **no MCP found**: 117

- **enterprise gated**: 45

- **solo reachable**: 117

- **bench tested**: 0

Entry facts were pulled by hand: 261 on 2026-08-24, 32 on 2026-08-25. The generated date above is only the date this site was baked. Both dates ship because both rot. 277 of the 293 entries are unique products; 16 are the same product listed in a second category and counted once here.

- [Search by capability](#search)

- [Install the MCP server](#install)

- [See the 144 official servers](mcp/official.md)

**Capability search**

## Ask for the job, not the category.

An agent does not want a data enrichment tool. It wants a person's title from a LinkedIn URL. Type the thing you are trying to do. This runs in your browser over a baked index: no backend, no query logging, and it keeps working with the network cable pulled out.

Search the directory

Official MCPCommunity MCPMCP unknownMCP not applicableNo MCP found
Free to startPaid, self-serveEnterprise leaningEnterprise onlyGate unknownGate not applicable

Ordering is fixed and published, never tuned and never purchasable. official MCP first, then community, then unknown, then n/a, then none-found; within each band gate order is free, paid, enterprise-leaning, enterprise-only, unknown; then alphabetical by name. Computed, never curated, never purchasable. With a query typed, matches are banded by relevance first and the rule above breaks every tie. An exact name match pins to the top and nothing else is boosted. The filters above run over the 277 unique products, so their totals sit below the 293 entry totals used by the [MCP status](mcp/index.md) and [gate](gates/index.md) views. Both numbers are correct and the difference is the 16 cross listings.

**The inversion**

## The tools sold as agents are the least usable by agents.

RevOps Infra is 22 of 23 reachable by an agent. Enablement & Coaching is 2 of 14. Gold is an official server, green is a community one. Every ratio below is read straight out of the category blocks in directory.json.

- [RevOps Infra](categories/revops-infra.md)**22** of 23 reachable

- [Data & Enrichment](categories/data-enrichment.md)**33** of 38 reachable

- [Conversation Intel](categories/conversation-intel.md)**20** of 24 reachable

- [Signals & Intent](categories/signals-intent-abm.md)**18** of 28 reachable

- [Video Prospecting](categories/video-prospecting.md)**9** of 14 reachable

- [Engagement & Outbound](categories/engagement-outbound.md)**17** of 27 reachable

- [Scheduling & Routing](categories/scheduling-routing.md)**8** of 14 reachable

- [MCP Layer](categories/mcp-infrastructure.md)**7** of 13 reachable

- [Proposals & Deals](categories/proposals-deals.md)**7** of 14 reachable

- [Inbound & PLG Chat](categories/inbound-plg-chat.md)**5** of 15 reachable

- [Email Deliverability](categories/email-deliverability.md)**4** of 13 reachable

- [AI SDRs](categories/ai-sdr-agents.md)**6** of 23 reachable

- [Community & Dark Social](categories/community-dark-social.md)**4** of 16 reachable

- [Forecasting & Revenue](categories/forecasting-revenue.md)**3** of 17 reachable

- [Enablement & Coaching](categories/enablement-coaching.md)**2** of 14 reachable

**Install the MCP server**

## Point your agent at the directory.

The server loads the baked file once at import and answers from memory. It makes zero outbound network requests, so it cannot be slow, cannot rate limit you, cannot cost anything, and cannot leak your query to a vendor. Everything network shaped happens in the weekly build.

```
{
 "mcpServers": {
 "gtm-directory": {
 "command": "uvx",
 "args": [
 "gtm-mcp-directory"
 ]
 }
 }
}
```

The package is not on PyPI yet, so this block is the shape the install will take rather than a working one-liner today. The server source is real and public: it lives in the [gtm-mcp-directory](https://github.com/andrewcmcguire/gtm-mcp-directory) repo and runs from a checkout right now.

**What it answers**

### find_tools

Which tools can do X, and can your agent actually reach them. Filters on category, MCP status, access gate and tier, and states the ordering rule it used.

**What it answers**

### get_tool

Every field on one entry, sources in full, plus the cross reference when the same product is listed in a second category.

**What it answers**

### whats_mcpd

The stat block. 293 entries, 144 official, 21 community, 117 none found, and 0 bench tested, scoped to a category when you ask for one.

**What it answers**

### list_categories

The 15 category files with their counts, gates and source markdown, reconciled against tools_recount.py at build time.

**The weekly diff**

## Get the changelog by email.

Once a week: new entries, dead endpoints, gate changes, and every tool that moved between MCP statuses. Assembled from the machine output, never written from thin air.

 Not wired yet

PLACEHOLDER. The list runs on Kit and the form action is deliberately empty until that endpoint is set. No address is collected today and nothing is sent anywhere.

**Submit a tool**

## Listing is free. Placement is not for sale.

Anyone can submit a tool. Every submission is verified against public sources before it is listed, and the verification is the product. No vendor can pay to be listed, to rank higher, to be featured, or to soften a note. BENCH-TESTED cannot be bought at any price.

- [Open the submission form](https://github.com/andrewcmcguire/gtm-mcp-directory/issues/new?template=tool-submission.yml)

- [Read what happens next](submit.md)

The submission queue is a GitHub issue form on the public gtm-mcp-directory repo. It is open now, and every submission is verified before it lists.

**The questions**

## Answers, not opinions.

The questions people actually ask about GTM tools, MCP servers and agents, answered from this data with the numbers generated at build time and the date stamped on every one. No tool versus tool verdicts, because 0 tools here have been bench tested.

- [Learn](learn/index.md) - Definitions, data and how to. What an MCP server is, what a GTM engineer is, which tools an agent can use for free, how to connect an assistant to a CRM.

- [The lists](lists/index.md) - 144 official servers, 57 free tiers. The same entries cut the ways people ask for them: by MCP status, by gate, by auth type, by category.

- [By job](jobs/index.md) - 55 jobs, 10 families. What an agent actually asks for, phrased from the agent's side, with the tools tagged against each one.

- [The data](data.md) - directory.json, free, no key. The whole directory as one JSON file, plus llms.txt and a markdown twin of every page on this site.

**Honesty**

## 0 bench tested, and that number is on the front page.

Every entry is RESEARCHED: facts from public sources with URLs, no usage claims, nobody has run the tool. BENCH-TESTED means Andrew personally ran it on a stated date. There are 0 of those, the number is published rather than hidden, and it is the proof the tier means something. 83 entries carry an access gate of unknown, 263 have no documentation URL recorded, and the 32 thinly sourced entries are named on the methodology page rather than quietly padded.

- [How an entry is made](methodology.md)

- [Browse all 277 products](tools/index.md)
