gp-mcp-server

Provides a Spring Boot Model Context Protocol (MCP) server (streamable HTTP transport) exposing Greenplum/PostgreSQL database tools (schema discovery and query execution) with API-key authentication, policy enforcement (query validation, row/byte limits, allow-lists, redaction), and observability features (health, metrics, tracing).

Evaluated Apr 04, 2026 (17d ago)
Repo ↗ Infrastructure mcp postgresql greenplum spring-boot database-proxy api-key-auth sql-policy streaming observability
⚙ Agent Friendliness
57
/ 100
Can an agent use this?
🔒 Security
66
/ 100
Is it safe for agents?
⚡ Reliability
29
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
80
Documentation
65
Error Messages
0
Auth Simplicity
75
Rate Limits
10

🔒 Security

TLS Enforcement
70
Auth Strength
80
Scope Granularity
60
Dep. Hygiene
30
Secret Handling
75

Positive signals: API-key authentication with encryption-key-based credential encryption (AES-256-GCM), method-level authorization (@PreAuthorize isAuthenticated()), and policy enforcement (SQL validation, schema/table allow-lists, row/byte limits, redaction, statement timeout). Unclear/unspecified: TLS requirement details (no explicit statement that HTTP is always HTTPS), rate limiting controls, dependency/Vulnerability management, and how errors are sanitized (to avoid leaking SQL/metadata). Also, admin endpoints and API key generation are mentioned; operational security depends on deployment hardening and strict access control.

⚡ Reliability

Uptime/SLA
20
Version Stability
25
Breaking Changes
20
Error Recovery
50
AF Security Reliability

Best When

You need an MCP-compatible database tool layer where agents must be constrained by SQL validation and governance controls, with API-key-based tenancy.

Avoid When

You cannot ensure TLS termination, secure secret management (encryption key and credentials), or you need strong guarantees about dependency/security posture without reviewing the actual implementation code.

Use Cases

  • Letting AI agents safely inspect database schemas and run constrained read-only queries against Greenplum/PostgreSQL
  • Building an MCP tool interface for data analysis workflows with enforced governance (allowed schemas/tables, result-size limits, redaction)
  • Providing streaming query results and server-side cursors for large read workloads
  • Centralizing query validation and safe execution controls for multi-tenant agent access via per-key credentials/pooling

Not For

  • Executing non-SELECT or write operations (not presented as supported)
  • Highly interactive admin usage without proper access controls (admin endpoints and API key generation are referenced)
  • Publicly exposing database access without TLS and strong API-key management
  • Workloads requiring complex transactional semantics or long-running stateful DB sessions beyond stated timeouts

Interface

REST API
Yes
GraphQL
No
gRPC
No
MCP Server
Yes
SDK
No
Webhooks
No

Authentication

Methods: X-API-Key header Authorization: Bearer
OAuth: No Scopes: No

Tool execution requires authentication (isAuthenticated()). API key format described as gpmcp_live_{id}.{secret}; execution depends on Spring Security principal set by ApiKeyAuthenticationFilter and method-level @PreAuthorize.

Pricing

Free tier: No
Requires CC: No

No pricing information provided; appears to be a self-hosted open-source server.

Agent Metadata

Pagination
tool-based (pagination mentioned for listSchemas/listTables; cursor-based pagination for query results)
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • Tool discovery (/mcp tools/list) is described as public while execution requires authentication; agents must provide valid API keys for tool calls.
  • Result-size controls (max-rows/max-bytes) may cause truncated/limited outputs; agents should adapt queries accordingly.
  • Cursor-based tools require correct session/cursor handling (open/fetch/close); agents may leak resources if closeCursor is not called.
  • Streaming/operation cancellation depends on operation IDs; agents may need to capture and use them for cancel.

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for gp-mcp-server.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-04-04.

8642
Packages Evaluated
17761
Need Evaluation
586
Need Re-evaluation
Community Powered