nexus-mcpSAFE
MCP server that delegates tasks to coding agents (Claude, Codex, Antigravity)
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
MCP server that delegates tasks to coding agents — Claude Code via the Claude Agent SDK, Codex via the Codex App Server, and Antigravity via the Antigravity SDK — from any MCP client.
Install
Backends are optional extras; install the ones you use.
uvx --with 'nexus-mcp[all]' nexus-mcp # run directly pip install 'nexus-mcp[claude]' # or install pip install 'nexus-mcp[codex]' # Codex only pip install 'nexus-mcp[antigravity]'
Claude Code MCP config:
{ "mcpServers": { "nexus": { "command": "uvx", "args": ["--with", "nexus-mcp[all]", "nexus-mcp"] } } }Authentication is the agent's own: log in with claude, or set ANTHROPIC_API_KEY; for Codex, log in with codex login (credentials in ~/.codex are shared). Antigravity uses GEMINI_API_KEY, or Vertex AI with GOOGLE_GENAI_USE_VERTEXAI, GOOGLE_CLOUD_PROJECT, and GOOGLE_CLOUD_LOCATION, authenticated through Application Default Credentials (ADC). It does not use Google-account login.
Windows: recent claude-agent-sdk releases ship no Windows wheel with a bundled CLI; install Claude Code so claude is on PATH.
Tool: prompt
Runs one agent turn and returns its final answer.
3056ede4e763OBSERVED · 2026-10-11Connect
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 mcp add nexus-mcp -- uvx nexus-mcp==2.1.1
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | WARN |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- declared (1 observation(s))
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (8)
return importlib.import_module(f"nexus_mcp.backends.{name}").pre-commit-config.yaml
.version-bump.json
{"file_path": "/etc/hosts"},outside = {"tool_name": "Write", "tool_input": {"file_path": "/etc/hosts"}}("full_access", "Write", {"file_path": "/etc/hosts"}, PermissionResultAllow),sudo mv mcp-publisher /usr/local/bin/
Gates applied: no_behavioural_pass.
3056ede4e763full audit observations/trust-audit/mcp-server/j7an__nexus-mcp.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-11 | 3056ede4e763 | SAFE | B | 89 | first audit |
Questions
What is the nexus-mcp MCP server?
MCP server that delegates tasks to coding agents (Claude, Codex, Antigravity)
Is nexus-mcp safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does nexus-mcp need?
It reads NEXUS_TEST_GEMINI_API_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 nexus-mcp run?
It speaks stdio, so it runs as a local process your client starts. It is published on PyPI as nexus-mcp.
How current is this page?
The grade is for one exact copy of the source (3056ede4e763), read on 2026-10-11. The repository is watched and re-audited when it changes.