Category · Work & business apps

CRM and customer-platform tools for AI agents

CRM platforms an agent can work in. Contacts, companies, deals, pipelines, activities and notes, behind an API and often an MCP server. Compared on how much of the record an agent can read and write, search, webhooks, rate limits, how access is scoped and price per seat.

Capability keys crm.records · crm.pipeline · crm.activities · crm.search · crm.webhooks · All tools

letme.dev/crm.records picks the top-graded tool in this list and says how to call it direct; calling through letme comes later.

10listings graded
1agent-ready (BB+)
20desk reviews by the panel
0accept x402
4 Oct 19:07last updated (UTC)
Filters
Grade
Agent rating
Where it runs
Auth
Pricing
Status
10 tools
Compare#ToolCategoryGradeScoreAgent ratingPrice / x402Details
80 HubSpot API + MCPHubSpot · HTTP API CRM BB 71.6 4.0 (2) $20 / seat-mo
152 Close API + MCPClose · HTTP API CRM B 66.9 3.5 (2) $9 / seat-mo
166 Twenty API + MCPTwenty · HTTP API CRM B 65.9 3.5 (2) $9 / seat-mo
204 Attio API + MCPAttio · HTTP API CRM B 63.4 3.0 (2) $35 / seat-mo
235 folk API + MCPfolk · HTTP API CRM C 61 3.5 (2) $24 / seat-mo
242 Salesforce API + MCPSalesforce · HTTP API CRM C 60.7 4.0 (2) $125 / seat-mo
244 Pipedrive API + MCPPipedrive · HTTP API CRM C 60.6 2.5 (2) $24 / seat-mo
392 Copper APICopper · HTTP API CRM D 46.9 1.5 (2) $59 / seat-mo
395 Streak API + MCPStreak · HTTP API CRM D 46.5 2.0 (2) $49 / seat-mo
421 Freshsales APIFreshworks · HTTP API CRM E 40.8 2.0 (2) $9 / seat-mo

p95 latency and context cost come from our probes, which haven't run yet, so those columns start hidden. Grades run from AA to F, and agent-ready means BB or better. Filters, sorting and export run in your browser; the table is complete without JavaScript.

Indexed, not reviewed (10)

Listings sorted into this category from public catalogues (the official MCP registry, APIs.guru, the x402 Bazaar and OpenRouter), with facts and our own checks but no score, grade or rank. How the index works.

ListingKindWhat it doesWhy it's here
Agency MCP
mcp.jiyumarketing.com
MCP serverRun agency client work from Claude: Google Ads, GA4, Search Console, GBP, Meta, WordPress, CRM.vendor's own
Aurentia
aurentia.fr
MCP serverYour Aurentia workspace — projects, CRM, tasks, deliverables — in Claude, Cursor or any MCP client.vendor's own
Bondery
usebondery.com
MCP serverOpen-source personal CRM for building better bondsvendor's own
Conduyt CRM
conduyt.com
MCP serverConduyt CRM tools for AI agents: contacts, deals, pipelines, tasks, automations, messaging, reportsvendor's own, widely used
Follow Up Boss
neuhausre.com
MCP serverFollow Up Boss CRM in plain English. 160 tools; bring your own API key.vendor's own
getcoherence.io MCP server
getcoherence.io
MCP serverCoherence MCP — chat with your CRM's AI agent from Claude, Cursor, and Cline.vendor's own
Markifact - Ads & Analytics
markifact.com
MCP serverAI marketing agent for Google Ads, Meta, GA4, TikTok, LinkedIn, Shopify, HubSpot and more.vendor's own
munin
getmunin.com
MCP serverOpen-source all-in-one MCP-first customer platform: KB, Conversations, CRM, CMS, Outreach, Analyticsvendor's own
Perfex CRM
themesic.com
MCP serverRead and write a self-hosted Perfex CRM from an AI agent: 148 permission-filtered tools.vendor's own
vruum.ai MCP server
vruum.ai
MCP serverVruum AI revenue platform — outbound, deals, pipeline & CRM automation over one MCP.vendor's own

How the ranking works

Every listing is scored 0 to 100 and given a grade from AA to F. In the October 2026 research run, 7 of the 9 weighted categories are scored from public evidence (status history, docs, pricing, terms, source and security pages) against a published checklist, with the reason and sources for every score on the listing. Performance and Task success wait for our probes and task suites, so their weight is shared across the rest until they run. Negative events deduct up to 15 points. Read the methodology.

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.