New Your team’s decisions, in one playbook every coding agent works from. Never answer your agent twice
// MCP SERVER RECORD

Dephq

Unverified
NPM@dephq/mcp
FRisk gradecritical blast radius
Catalogue entry updated 32 days ago
Auth postureNot probedno remote endpoint probed yet
Tools121 Destructive · 1 Execute · 4 Write · 6 Read
Worst categoryDestructivegrade tracks the peak, not the average
Capability mix
Destructive 1Execute 1Write 4Read 6
What it can reach
Ingests untrusted inputTouches secretsReaches networkRuns codeTouches filesChanges permissionsSends external commsPersistsDeletes dataMoves money
Tools 12
dephq_app_unpublishDestructiveHighdephq_app_checkExecuteMediumdephq_app_publishWriteHighdephq_app_rollbackWriteHighdephq_project_initWriteMedium
View all 12 tools
dephq_project_syncWriteHighdephq_accountReadLowdephq_app_showReadLowdephq_app_versionsReadLowdephq_apps_listReadLowdephq_project_validateReadLowdephq_sync_statusReadLow
These definitions cost 1,918 tokens of context →
Change history
No change history on record for this server.
Recommended policy
dephq_app_unpublishdeny
dephq_app_checkrequire approval
dephq_app_publishrate limit
Read-only toolsallow
Full policy breakdown with enforcement rules →

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

// RUNNING THIS SERVER
DIRECT INSTALL npx -y @dephq/mcp

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 →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.