Skip to main content
Glama
AmirTlinov

PostgreSQL API SSH MCP Server

by AmirTlinov

SentryFrogg MCP Server

Русская версияDocsMCP configurationIntegration stackChangelog

License: MIT Node.js >=18 CI

SentryFrogg is a stdio-based Model Context Protocol (MCP) server that gives LLM agents a production-grade toolbox for PostgreSQL, SSH (incl. SFTP), and HTTP. Use it when you want real infrastructure access without glue scripts: profiles, streaming pipelines, runbooks, and auditability are built in.

If you want your agent to move real data (API ↔ SFTP ↔ Postgres), run controlled SSH ops, and leave a traceable trail — this is the server.

Why SentryFrogg

  • One profile system across Postgres, SSH, and HTTP.

  • Streaming pipelines between HTTP, SFTP, and Postgres for large payloads.

  • Reliability primitives: retry/backoff, pagination, timeouts.

  • Runbooks + state for multi-step workflows and repeatable ops.

  • Intent layer with capability registry, previewed plans, and evidence bundles.

  • Observability with trace/span metadata and audit logs (redacted).

  • Encrypted local profile store (AES-256-GCM).

  • Safe-by-default local writes (no overwrite unless overwrite: true).

  • Optional unsafe local mode for full agent autonomy (local exec + filesystem).

Related MCP server: pg-mcp

Use cases

  • Sync or backfill data between APIs, SFTP drops, and PostgreSQL.

  • Run controlled remote operations via SSH with auditability.

  • Build repeatable incident runbooks for agents and operators.

Quick examples

Ingest JSONL into Postgres:

{ "action": "run", "flow": "http_to_postgres", "http": { "url": "https://example.com/events.jsonl" }, "postgres": { "profile_name": "default", "table": "events" }, "format": "jsonl", "batch_size": 500 }

Export Postgres to SFTP:

{ "action": "run", "flow": "postgres_to_sftp", "postgres": { "profile_name": "default", "table": "events" }, "format": "csv", "sftp": { "profile_name": "default", "remote_path": "/tmp/events.csv", "overwrite": true } }

Quick start

  1. Install: npm install

  2. Configure your MCP client (stdio):

    { "mcpServers": { "sentryfrogg": { "command": "node", "args": ["/absolute/path/to/sentryfrogg_server.cjs"] } } }

    More details: mcp_config.md.

  3. Start: npm start

  4. In your MCP client: call help, then profile_upsert for PostgreSQL/SSH

Tools

  • help

  • mcp_psql_manager

  • mcp_ssh_manager

  • mcp_api_client

  • mcp_state

  • mcp_runbook

  • mcp_project

  • mcp_context

  • mcp_workspace

  • mcp_capability

  • mcp_intent

  • mcp_evidence

  • mcp_alias

  • mcp_preset

  • mcp_audit

  • mcp_pipeline

  • mcp_local (unsafe, opt-in)

Short aliases are also available (sql, psql, ssh, http, api, state, runbook, workspace, pipeline; plus local when unsafe mode is enabled).

Reference + examples: docs/tools.md.

Intent UX

  • Define capabilities in capabilities.json (override path via MCP_CAPABILITIES_PATH).

  • Context snapshots are stored in context.json (override path via MCP_CONTEXT_PATH).

  • mcp_intent compiles to a runbook plan, dry-run by default; write/mixed effects require apply: true.

  • Evidence bundles are stored under .sentryfrogg/evidence (override path via MCP_EVIDENCE_DIR).

Development

  • npm run check

  • npm test

  • npm run smoke (Docker) — see integration/README.md

Security

This server can execute SQL/SSH/HTTP by design. Run it only in environments you trust.

  • Vulnerability reporting: SECURITY.md

  • Public release checklist: PUBLIC_RELEASE_CHECKLIST.md

License

MIT — see LICENSE.

Install Server
A
security – no known vulnerabilities
A
license - permissive license
A
quality - confirmed to work

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/AmirTlinov/PSQL_SSH_API_MCP'

If you have feedback or need assistance with the MCP directory API, please join our Discord server