// MCP SERVER RECORD

Openai

Unverified
REPOrobotlearning123/gpt2agent
FRisk gradecritical blast radius
Catalogue entry updated 6 days ago
Auth postureNot probedno remote endpoint probed yet
Tools255 Execute · 3 Write · 17 Read
Worst categoryExecutegrade tracks the peak, not the average
Capability mix
Execute 5Write 3Read 17
What it can reach
Ingests untrusted inputTouches secretsReaches networkRuns codeTouches filesChanges permissionsSends external commsPersistsDeletes dataMoves money
Tools 25
canvas_executeExecuteHighcode_interpreterExecuteHighdeep_researchExecuteMediumdeep_research_heavyExecuteMediumgenerate_imageExecuteHigh
View all 25 tools
codex_task_createWriteMediumcustom_instructions_setWriteMediummemory_create_via_chatWriteMediumaccount_statusReadLowagentReadLowchatReadLowcustom_instructions_getReadLowget_conversationReadLowget_file_download_urlReadLowget_file_infoReadLowgpt_chatReadLowlist_appsReadLowlist_codex_envsReadMediumlist_codex_tasksReadLowlist_conversationsReadMediumlist_custom_gptsReadLowlist_modelsReadLowlist_tasksReadLowmemory_listReadLowmemory_searchReadLow
Change history
No changes recorded since first scan. Watched servers surface a diff within the hour.
Recommended policy
canvas_executerequire approval
codex_task_createrate limit
Read-only toolsallow
Full policy breakdown with enforcement rules →
// 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.