Axon
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Axonlocalize the bug causing the crash in user auth"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Axon
Root-cause debugging & vulnerability plugin for AI coding agents.
Axon traces a fault signal back to its source — like the axon that carries a neuron's signal. It gives an agent the tools to localize bugs, verify fixes, and find security vulnerabilities with high precision.
Companion to Cortex. Cortex is the context/graph brain; Axon is the debugging + security tracer. Cortex is optional — Axon runs fully standalone.
Why Axon
Research shows no agent hits "90% detect everything" universally. Axon reaches ≥90% on a defined slice by stacking four proven levers:
Context grounding — code graph + retrieval, built-in (no external deps).
Executable verification — reproduce → fix → confirm FAIL→PASS.
Adversarial triage — a refuter agent must disprove each finding → kills false positives (the security adoption killer).
Static-analysis grounding — SAST output the agent filters/confirms.
Related MCP server: yo-bug
Plug-and-play by design
Zero-config. Install → run. Nothing else needed.
No GPU, no model download, no daemon. Retrieval defaults to BM25 + ripgrep.
Optional accelerators, auto-detected, never required:
Cortex → richer code graph/impact. Absent → built-in provider.
Local embedding model → semantic re-rank. Absent → BM25 floor.
CodeQL → deeper security. Absent → Semgrep.
Same agent tools and output shape on every rung. Accelerators only improve quality/speed; their absence never breaks a feature.
Tools (MCP)
axon serve exposes 11 tools over MCP (stdio): index, graph_context,
search, localize, run_tests, repro, verify_fix, spectrum,
sast_scan, refute, triage.
Quickstart
pip install -e . # or: uvx axon
axon doctor # environment + active backend
axon index <repo> # build/refresh the code index
axon serve # start the MCP server (stdio)Point any MCP host (Claude Code, etc.) at axon serve. Runs with no Cortex,
no GPU, no model download.
Install as a Claude Code plugin
/plugin marketplace add <path-or-git-url-of-this-repo>
/plugin install axon@axonThe first server start bootstraps a private plugin venv and needs python3.
Semgrep-backed SAST is optional: install it with pip install 'axon-debug[security]'
into the plugin venv, or have semgrep available on PATH.
Versioning: Axon uses semver; bump pyproject.toml,
.claude-plugin/plugin.json, and .claude-plugin/marketplace.json together
on release.
Status
v0 built and verified — 35 tests pass, 6 phased commits. Core machinery
(providers, localize, verify-fix loop, security triage) works and composes
end-to-end. The frozen benchmark run (SWE-bench + PrimeVul) is the next
milestone — see docs/VERIFICATION.md for exactly
what is proven vs. still unmeasured, and docs/PLAN.md for
the design.
Security
Report vulnerabilities privately through the process in SECURITY.md.
Public repository hardening requirements are tracked in
docs/GITHUB_SECURITY.md.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
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/alilfrances/Axon'
If you have feedback or need assistance with the MCP directory API, please join our Discord server