A-

mcp.specproof.ai

Item: mcp.specproof.ai
Rating: 91
Author: wmcp.sh

https://mcp.specproof.ai/

91/100 · MCP Trust Grade · checked 4h ago · MCP 2024-11-05

✓ Watched since 2026-06-03 — behavioral baseline locked. We re-check this server's tool surface on a schedule; if it adds, removes, or silently rewrites a tool (rug-pull), we record it.

What it offers — 8 tools · Database

search_specifications

Search across 3GPP and IETF specification documents using full-text search. Returns ranked results with content previews.

semantic_search

Perform semantic search using vector embeddings with FAISS acceleration for better conceptual matching.

get_document_content

Retrieve specific content from a specification document by filename, with optional page range and section filtering.

list_documents

List available specification documents with filtering options.

get_database_stats

Get comprehensive database and system statistics including document counts, search capabilities, and performance metrics.

search_contributions

Search 3GPP contribution documents by various criteria including document number, working group, meeting, work item, and agenda item.

get_contribution_content

Get the full content of a 3GPP contribution document by its document number.

semantic_search_contributions

Perform semantic search on 3GPP contribution documents using FAISS-accelerated vector similarity search.

Spec conformance20%100

✓ initialize → protocolVersion 2024-11-05
✓ initialize HTTP 200
✓ unknown method → -32601
✓ tools/list → 8 tools
✓ every tool has name + inputSchema

Security (OWASP MCP)30%100

8 tools scanned
no injection markup
no secret-path refs

Reliability / performance20%84

single-probe latency 1450ms (PRELIMINARY — continuous uptime/p95 from proxy telemetry lands in v2)

Tool hygiene15%73

88% of tools have typed inputSchema
0/8 declare outputSchema
no unannotated destructive tools

Transparency / provenance15%90

HTTPS ✓
RFC 9728 oauth-protected-resource metadata ✓
advertises protocol 2024-11-05

Observed behavior

No proxied traffic observed for this host yet. Connect it at /connect and its grade gains a measured Reliability score + per-tool behavioral evidence — the half a static scan can't produce.

Findings

No blocking issues found in the static + spec checks.

Grade another server

We re-grade mcp.specproof.ai on a schedule and alert your Slack/webhook the moment its tools change or its grade drops — rug-pull insurance for the connection.

Share this report card

A 1200×630 card with the grade + audit — drop it in a post, Slack, or your repo.

MCP Trust report card — mcp.specproof.ai grade A-

Share on X Open card image

https://wmcp.sh/mcp/grade/mcp.specproof.ai

Embed this grade

A live badge — it re-verifies itself and shows current stability. Static scorecards can't. Paste it in your README or site to show users you're independently audited.

Markdown (for your README)

[![MCP Trust Grade A-](https://wmcp.sh/mcp/grade/mcp.specproof.ai/badge.svg)](https://wmcp.sh/mcp/grade/mcp.specproof.ai)

HTML

<a href="https://wmcp.sh/mcp/grade/mcp.specproof.ai"><img src="https://wmcp.sh/mcp/grade/mcp.specproof.ai/badge.svg" alt="MCP Trust Grade A- · wmcp.sh"></a>

Agents: check this before connecting

Add the wmcp.sh trust oracle as an MCP server and call grade_mcp_server / check_mcp_drift in your agent's pre-connection gate:

https://wmcp.sh/mcp/trust

How this grade is computed. An open, independent rubric — Spec conformance (20%), Security mapped to the OWASP MCP Top 10 (30%), Reliability (20%), Tool hygiene (15%), Transparency (15%) — run by connecting to the server and inspecting its real MCP surface. The grade is free and identical whether or not the operator pays. v1 uses static + spec signals from a single connection; continuous uptime, real latency, and annotation-truthing (declared readOnly vs observed behavior) layer on via the wmcp.sh proxy.