AxonSAFE
Graph-powered code intelligence engine — indexes codebases into a knowledge graph, exposed via MCP tools for AI agents and a CLI for developers.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://pypi.org/project/axoniq/) [](https://pepy.tech/projects/axoniq) [](https://pepy.tech/projects/axoniq) [](https://github.com/harshkedia177/axon) [](https://github.com/harshkedia177/axon/blob/main/LICENSE)
The knowledge graph for your codebase — explore it visually, or let your AI agent query it.
Indexes any codebase into a structural knowledge graph — every dependency, call chain, cluster, and execution flow. Explore it through an interactive web dashboard with force-directed graph visualization, or expose it through MCP tools so AI agents get full structural understanding in every tool call.
$ axon analyze . Walking files... 142 files found Parsing code... 142/142 Tracing calls... 847 calls resolved Analyzing types... 234 type relationships Detecting communities... 8 clusters found Detecting execution flows... 34 processes found Finding dead code... 12 unreachable symbols Analyzing git history... 18 coupled file pairs Generating embeddings... 623 vectors stored Done in 4.2s — 623 symbols, 1,847 edges, 8 clusters, 34 flows
Then explore your codebase visually:
axon ui # Opens interactive dashboard at localhost:8420
Three views, one command:
- Explorer — Interactive force-directed graph (Sigma.js + WebGL). Click any node to see its code, callers, callees, impact radius, and community. Community hull overlays show architectural clusters at a glance.
- Analysis
460d4952f770OBSERVED · 2026-09-27Connect
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.
claude mcp add axon-ui -- npx -y [email protected]
{
"mcpServers": {
"axon-ui": {
"command": "npx",
"args": [
"-y",
"[email protected]"
]
}
}
}Exposed tools (11)
9 read · 2 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
analysis | read | Switch to Analysis view |
axon_cypher | write | Execute a raw Cypher query against the knowledge graph. |
axon_dead_code | read | List all symbols detected as dead (unreachable) code. |
axon_list_repos | read | List all indexed repositories with their stats. |
communities | read | Open Communities tab |
cypher | read | Switch to Cypher view |
dead-code | read | Open Dead Code tab |
explorer | read | Switch to Explorer view |
hulls | read | Toggle community hulls |
minimap | read | Toggle minimap |
reindex | write | Trigger reindex |
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 | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (3 observation(s))
- Network
- declared (4 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (8)
response = client.get("/file?path=../../etc/passwd")return_value={"host_url": "http://127.0.0.1:8420", "mcp_url": "http://127.0.0.1:8420/mcp"},return_value={"host_url": "http://127.0.0.1:8420", "mcp_url": "http://127.0.0.1:8420/mcp"},assert "http://127.0.0.1:8420" in result.output
mock_open.assert_called_once_with("http://127.0.0.1:8420")app.state.host_url = "http://127.0.0.1:8420"
@sigma/node-border, class-variance-authority, clsx, cmdk, dompurify, graphology, graphology-layout, graphology-layout-forceatlas2
Gates applied: no_behavioural_pass, no_license.
460d4952f770full audit observations/trust-audit/mcp-server/harshkedia177__axon-1.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 |
|---|---|---|---|---|---|
| 2026-09-27 | 460d4952f770 | SAFE | B | 89 | first audit |
Questions
What is the Axon MCP server?
Graph-powered code intelligence engine — indexes codebases into a knowledge graph, exposed via MCP tools for AI agents and a CLI for developers.
What tools does Axon expose?
11 in total: 9 read-only, 2 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Axon 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 Axon need?
No credential environment variables were found in its source, so it appears to need none.
How does Axon run?
It speaks stdio and streamable-http, so it runs as a local process your client starts. It is published on npm as axon-ui at 0.1.0.
How current is this page?
The grade is for one exact copy of the source (460d4952f770), read on 2026-09-27. The repository is watched and re-audited when it changes.