MCP REGISTRY FOR AGENTS DOCS PRICING CONTROL YOUR AGENTS

// MCP SERVER RECORD

Slack

Official

REPOmodelcontextprotocol/server-slackNPM@modelcontextprotocol/server-slack

FRisk gradecritical blast radius

Last checked 112 days ago·seed·Watched hourly for changes

Auth postureNot probedno remote endpoint probed yet

Tools83 Write · 5 Read

Worst categoryWritegrade tracks the peak, not the average

Capability mix

Write 3Read 5

What it can reach

Ingests untrusted inputTouches secretsReaches networkRuns codeTouches filesChanges permissionsSends external commsPersistsDeletes dataMoves money

Exfiltration pathReads content an attacker can plant and can send data outward — a prompt-injection-to-exfiltration route.

Tools 8

slack_add_reactionWriteLow slack_post_messageWriteMedium slack_reply_to_threadWriteMedium slack_get_channel_historyReadLow slack_get_thread_repliesReadLow

View all 8 tools

slack_get_user_profileReadLow slack_get_usersReadLow slack_list_channelsReadLow

Change history

No change history on record for this server. Watched servers surface a diff within the hour.

Recommended policy

Read-only toolsallow

Full policy breakdown with enforcement rules →

The upstream implementation is archived but remains widely installed. The classifications and policies here still apply to deployed copies.

This record as markdown: /tools/slack.md — append .md to any tool or server page.

// RUNNING THIS SERVER

DIRECT INSTALL npx -y @modelcontextprotocol/server-slack

Installed this way, nothing enforces the recommended policy above — calls run exactly as the agent makes them.

// LOOK UP ANOTHER SERVER

Every MCP server has a record like this.

Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.

Teams ship this data inside their own products. See what a licence covers →