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

Mcp Agentcore

Unverified
REPOhttps://packagesmcp-perception-production.up.railway.app/mcp
DRisk gradehigh blast radius
Catalogue entry updated 38 days ago
Auth postureOPENCORS not exposed · no rate limit seen
Tools81 Execute · 2 Write · 4 Read · 1 Other
Worst categoryExecutegrade tracks the peak, not the average
Capability mix
Execute 1Write 2Read 4Other 1
What it can reach
Ingests untrusted inputTouches secretsReaches networkRuns codeTouches filesChanges permissionsSends external commsPersistsDeletes dataMoves money
Tools 8
perception_classifyExecuteHighgns_roll_epochWriteMediumperception_weatherWriteMediumgns_get_compliance_reportReadLowgns_get_trust_scoreReadLow
View all 8 tools
gns_verify_chainReadLowperception_fetch_tileReadLowperception_embedOtherLow
These definitions cost 1,140 tokens of context →
Change history
No change history on record for this server.
Recommended policy
perception_classifyrequire approval
gns_roll_epochrate limit
Read-only toolsallow
Full policy breakdown with enforcement rules →

This record as markdown: /tools/com-geiant-mcp-agentcore.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.