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

Adia Ai

Unverified
NPM@adia-ai/mcp
CRisk gradenotable
Catalogue entry updated 18 days ago
Auth postureNot probedno remote endpoint probed yet
Tools431 Execute · 7 Write · 34 Read · 1 Other
Worst categoryExecutegrade tracks the peak, not the average
Capability mix
Execute 1Write 7Read 34Other 1
What it can reach
Ingests untrusted inputTouches secretsReaches networkRuns codeTouches filesChanges permissionsSends external commsPersistsDeletes dataMoves money
Tools 43
run_evalExecuteMediumconvert_htmlWriteMediumgenerate_uiWriteMediumplan_app_stateWriteMediumrefine_compositionWriteMedium
View all 43 tools
report_issueWriteMediumresolve_compositionWriteMediumscaffold_componentWriteMediumassemble_contextReadLowaudit_structureReadLowcheck_anti_patternsReadLowclassify_intentReadLowcompose_from_chunksReadLowfactory_statusReadLowget_catalog_ladderReadLowget_catalog_tiersReadLowget_chunkReadLowget_component_mapReadLowget_compositionReadLowget_graphReadLowget_quality_metricsReadLowget_registry_mapReadLowget_stateReadLowget_training_gapsReadLowget_traitsReadLowget_wiring_catalogReadLowget_wiring_registryReadLowlist_patternsReadLowlookup_chunkReadLowlookup_componentReadLoworient_appReadLowprotocol_statusReadLowrefine_uiReadLowscaffold_appReadLowscaffold_pageReadLowsearch_chunksReadLowsearch_patternsReadLowserver_statusReadLowvalidate_documentReadMediumvalidate_schemaReadLowverify_surfaceReadLowzettel_statsReadLowsubmit_feedbackOtherLow
Change history
No change history on record for this server.
Recommended policy
run_evalrequire approval
convert_htmlrate limit
Read-only toolsallow
Full policy breakdown with enforcement rules →

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

// RUNNING THIS SERVER
DIRECT INSTALL npx -y @adia-ai/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.