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

Postgres

Unverified
NPM@allensandiego/postgres-mcp-server
FRisk gradecritical blast radius
Catalogue entry updated 4 days ago
Auth postureNot probedno remote endpoint probed yet
Tools82 Execute · 1 Write · 5 Read
Worst categoryExecutegrade tracks the peak, not the average
Capability mix
Execute 2Write 1Read 5
What it can reach
Ingests untrusted inputTouches secretsReaches networkRuns codeTouches filesChanges permissionsSends external commsPersistsDeletes dataMoves money
Tools 8
run_queryExecuteHighrun_write_queryExecuteHighset_roleWriteMediumdescribe_tableReadLowlist_databasesReadLow
View all 8 tools
list_permissionsReadLowlist_rolesReadLowlist_tablesReadLow
These definitions cost 833 tokens of context →
Change history
No change history on record for this server.
Recommended policy
run_queryrequire approval
set_rolerate limit
Read-only toolsallow
Full policy breakdown with enforcement rules →

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

// RUNNING THIS SERVER
DIRECT INSTALL npx -y @allensandiego/postgres-mcp-server

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.