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

Agent Custody

Unverified
REPOch4r10t33r/agent-custody
FRisk gradecritical blast radius
Catalogue entry updated 24 days ago
Auth postureNot probedno remote endpoint probed yet
Tools142 Destructive · 1 Write · 11 Other
Worst categoryDestructivegrade tracks the peak, not the average
Capability mix
Destructive 2Write 1Other 11
What it can reach
Ingests untrusted inputTouches secretsReaches networkRuns codeTouches filesChanges permissionsSends external commsPersistsDeletes dataMoves money
Tools 14
memory.forgetDestructiveHighmemory.sweepDestructiveCriticalmemory.writeWriteMediumcustomer.lookupOtherLowecho.sayOtherLow
View all 14 tools
memory.confirmOtherLowmemory.getOtherLowmemory.historyOtherLowmemory.holdOtherLowmemory.readOtherLowmemory.releaseOtherLowmemory.retractOtherLowstripe.payoutOtherLowstripe.refundOtherLow
Change history
No change history on record for this server.
Recommended policy
memory.forgetdeny
memory.writerate limit
Read-only toolsallow
Full policy breakdown with enforcement rules →

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

// 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.