ModelsAtlas
Explore
Atlas / MCP servers / convergeqa / convergeqa-reviews

convergeqa-reviewsBLOCK

mcp/convergeqa/convergeqa-mcp
MCP server by convergeqa · Audited 2026-10-12
⚑ Report / re-scanSource ↗

Stdio MCP servers for ConvergeQA multi-model document review

Verdict
BLOCK
Grade
D
Trust score
69 /100
Exposed tools
—
Transport
stdio
License
MIT
Stars
0
01

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

ConvergeQA is a multi-model document review system with public verification receipts. Its panels challenge thinking, surface disagreements, and document review evidence, while the responsible individual decides what to accept, reject, or revise.

This package exposes two stdio MCP servers:

  • convergeqa-mcp reviews (or convergeqa-mcp-reviews): Critique and Iterate review tools.
  • convergeqa-mcp compare (or convergeqa-mcp-compare): Compare due-diligence review tools.

Both servers delegate to the same CLI client contracts used by ConvergeQA agent tooling. Reviews consume paid credits. The servers read a ConvergeQA Developer API key or service-account key from environment variables at runtime, and the tool never stores keys.

Links

  • API keys: https://convergeqa.net/developers
  • Pricing and credits: https://convergeqa.net/pricing
  • Agent overview: https://convergeqa.net/agents
  • Trust: https://convergeqa.net/trust
  • LLM reference: https://convergeqa.net/llms.txt

Install

From PyPI:

uvx convergeqa-mcp reviews
uvx convergeqa-mcp compare
pipx run convergeqa-mcp reviews
pipx run convergeqa-mcp compare

Or directly from Git:

uvx --from git+https://github.com/convergeqa/convergeqa-mcp.git convergeqa-mcp-reviews
uvx --from git+https://github.com/convergeqa/convergeqa-mcp.git convergeqa-mcp-compare

Claude Code

Set CONVERGEQA_API_KEY or CONVERGEQA_SERVICE_ACCOUNT_KEY before starting your MCP client. The default key names are uppercase environment variables.

claude mcp add convergeqa-reviews --env CONVERGEQA_API_KEY=$CONVERGEQA_API_KEY -- uvx convergeqa-mcp reviews

Add Compare as a second server:

claude mcp add convergeqa-compare --env CONVERGEQA_API_KEY=$CONVERGEQA_API_KEY -- uvx convergeqa-mcp compare

Claude Desktop

Example claude_desktop_config.json:

{
"m
Read from source at commit 82146c27b8bcOBSERVED · 2026-10-12
Advertisement
02

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.

claude-code (pypi)
claude mcp add convergeqa-mcp --env CONVERGEQA_API_KEY=${CONVERGEQA_API_KEY} --env CONVERGEQA_SERVICE_ACCOUNT_KEY=${CONVERGEQA_SERVICE_ACCOUNT_KEY} -- uvx convergeqa-mcp==0.2.0 compare
03

Trust audit

BLOCKgrade D · trust 69/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codeFAIL
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
declared (3 observation(s))
Network
declared (5 observation(s))
Shell
none-observed
Dependencies
pinned
Secrets in source
none-found

Findings (5)

HIGHFilesystem / path · fs.credential_store · CWE-22, CWE-59
src/convergeqa_mcp/packet_secret_scan.py:47
"id_rsa",
Why it matters. touches a credential store
HIGHFilesystem / path · fs.credential_store · CWE-22, CWE-59
src/convergeqa_mcp/packet_secret_scan.py:48
"id_ed25519",
Why it matters. touches a credential store
HIGHFilesystem / path · fs.credential_store · CWE-22, CWE-59
src/convergeqa_mcp/packet_secret_scan.py:49
"id_ecdsa",
Why it matters. touches a credential store
LOWInventory / provenance · mcp.no_tools_extracted · CWE-1104
registry/compare/server.json
Why it matters. the tool list is enumerated at runtime by tools/list, not declared in source
Fix. the page says so rather than showing an empty table
INFOPrompt injection · prompt.credential_read · CWE-94, CWE-1427
README.md:13
Both servers delegate to the same CLI client contracts used by ConvergeQA agent tooling. Reviews consume paid credits. The servers read a ConvergeQA Developer API key or service-account key from envir
Why it matters. asks the agent to read credentials

Gates applied: no_behavioural_pass.

Audited 2026-10-12 · audit v0.4.1 · source sha 82146c27b8bcfull audit observations/trust-audit/mcp-server/convergeqa__convergeqa-mcp.json · Report an issue / request a re-scan
04

Audit history

Every audit this server has had. A grade with a past is a grade somebody is still checking.

DateSourceVerdictGradeScoreChange
2026-10-1282146c27b8bcBLOCKD69first audit
05

Questions

What is the convergeqa-reviews MCP server?

Stdio MCP servers for ConvergeQA multi-model document review

Is convergeqa-reviews safe to connect to an agent?

No — not without reading the findings first. The audit graded it D (69/100) and found 3 critical or high issues in the source. Each one is listed on this page with the file and line it is on.

What credentials does convergeqa-reviews need?

It reads CONVERGEQA_API_KEY and CONVERGEQA_SERVICE_ACCOUNT_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.

How does convergeqa-reviews run?

It speaks stdio, so it runs as a local process your client starts. It is published on PyPI as convergeqa-mcp.

How current is this page?

The grade is for one exact copy of the source (82146c27b8bc), read on 2026-10-12. The repository is watched and re-audited when it changes.

Advertisement