Safe-by-default SQL guardrails for AI agents. MCP server for Postgres over stdio + Streamable HTTP: parses every statement with a real SQL AST, enforces a per-table access policy, and audits before the query runs.
Inferred from the transports this listing declares (stdio). A client not listed here hasn’t been ruled out — it just isn’t something Forge can confirm.
DATABASE_URLAPI keyrequiredPostgres connection string the agent's queries run against. Give it a least-privilege role: Midplane constrains what SQL is allowed, it does not widen or narrow what the role itself can reach.
Declared by the author in the official MCP registry. Forge does not store, broker, or ever see these values — the config below is scaffolded with placeholders you fill in locally.
Verification confirms publisher identity (repo ownership), not code safety. The security scan covers known CVEs and suspicious install scripts.
Read out of the source npm actually ships, at scan time. The package was never executed. Tools registered dynamically at runtime, or hidden inside bundled or minified code, can be missed — so this is a floor on the tool surface, not a complete census of it.
queryParses the SQL with libpg_query, applies Midplane policy (table_access, multi_statement, tenant_scope, parse_error), audits the call, and returns rows on ALLOW. Denials return policy_rule + reason; the call is still audited. Required `intent` field captures why the query is being run (visible in au…Parses the SQL with libpg_query, applies Midplane policy (table_access, multi_statement, tenant_scope, parse_error), audits the call, and returns rows on ALLOW. Denials return policy_rule + reason; the call is still audited. Required `intent` field captures why the query is being run (visible in au…
No input schema was published for this tool.
list_tablesRouted through the same policy + audit pipeline. Defaults to the 'public' schema.Routed through the same policy + audit pipeline. Defaults to the 'public' schema.
No input schema was published for this tool.
describe_tableReturns column name, data type, nullability, and default. Routed through the policy + audit pipeline.Returns column name, data type, nullability, and default. Routed through the policy + audit pipeline.
No input schema was published for this tool.
list_databasesReturns each database's name, whether tenant_scope is enforced, and its table_access default. Use this to discover which `database` values to pass to `query`, `describe_table`, and `list_tables`.Returns each database's name, whether tenant_scope is enforced, and its table_access default. Use this to discover which `database` values to pass to `query`, `describe_table`, and `list_tables`.
No input schema was published for this tool.
check_approvalPoll a held write's approval status WITHOUT running anything. Use this to wait — it is cheap, safe to call repeatedly, and never consumes the approval. Returns pending (with its deadline), approved (call query again with the same sql and intent to actually execute it), executed (already ran — do no…Poll a held write's approval status WITHOUT running anything. Use this to wait — it is cheap, safe to call repeatedly, and never consumes the approval. Returns pending (with its deadline), approved (call query again with the same sql and intent to actually execute it), executed (already ran — do no…
No input schema was published for this tool.
5 of 5 tools published a description.
Tool names and descriptions are written by the publisher and shown verbatim as inert text. They are the strings an MCP client passes to a model, so Forge scans them for prompt-injection patterns — any finding appears with the security scan above. “Privileged” is a keyword match on the tool name, not an audit of what the tool does: a benign-sounding name can still do anything.
Safe-by-default SQL guardrails for AI agents. MCP server for Postgres over stdio + Streamable HTTP: parses every statement with a real SQL AST, enforces a per-table access policy, and audits before the query runs.
Linked names open Forge’s index of every entry observed exposing that tool. Browse all indexed tools.
The crawl stopped at the 60-package limit. The rest of the tree was never resolved.
36 more resolved packages are not drawn here (display cap: 24). Every dependency carrying an advisory is drawn regardless of the cap. Full inventory (CycloneDX SBOM)
40 declared dependencies never landed in the tree. They are missing from Forge's resolution, not from the package.
+28 more not listed. The counts by reason above cover all of them.
Not followed: optionalDependencies, peerDependencies. This tree covers runtime dependencies only, so anything those pull in was never resolved.