Axon ProSAFE
Enterprise-grade graph-powered code intelligence engine. Deep structural awareness for Laravel, PHP, Python, and JS. Powers AI agents with high-fidelity architectural context via MCP & Neo4j.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://github.com/talhamsajid/axon-pro/releases) [](https://opensource.org/licenses/MIT) [](https://www.python.org/) [](https://github.com/talhamsajid/homebrew-tap)
The Enterprise-grade graph-powered code intelligence engine. Axon Pro transforms flat codebases into structural knowledge graphs, providing AI agents and developers with 100% precise architectural awareness across polyglot microservices and modern web frameworks.
axon-pro analyze . Phase 1: Walking files... 1,242 files found Phase 3: Parsing code... 1,242/1,242 Phase 5: Tracing calls... 8,472 calls resolved Phase 7: Analyzing types... 2,341 type relationships Phase 9: Detecting execution flows... 156 processes found Phase 12: Linking Laravel Templates... 42 views connected Done in 12.4s — 4,623 symbols, 15,847 edges, 156 flows
💎 Why Axon Pro?
For AI Agents (Claude Code, Cursor, Windsurf):
- Deep Polyglot Support: Understands cross-language dependencies (PHP, Python, Java, TS).
- High-Fidelity Context: Moves beyond "text similarity" to "structural truth."
- Architectural Awareness: AI agents can finally see the "blast radius" of their changes.
- Flow Tracing: Traces execution from a Route, through Middleware, into a Controller, and out to a View or Background Job.
For Engineering Teams:
- Zero Cloud Footprint: Runs locally. No data leakage, no third-party API costs.
- Refactoring Safety: Instant impact analysis for complex legacy codebases.
- Onboarding Speed: New developers can query the architecture using natural language or Cypher.
- Technical Debt Audit: Automatica
c98785cc109dOBSERVED · 2026-10-08Connect
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-pro -- uvx axon-pro
{
"mcpServers": {
"axon-pro": {
"command": "uvx",
"args": [
"axon-pro"
]
}
}
}Exposed tools (11)
10 read · 1 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
axon_pro_architecture | read | Get a high-level architectural overview of the project (Models, Controllers, Jobs, etc). |
axon_pro_check_nplus1 | read | Scan for potential N+1 query patterns or heavy database usage in the indexed code. |
axon_pro_cypher | write | Execute a raw Cypher query against the knowledge graph. |
axon_pro_dead_code | read | List all detected dead code in the repository. |
axon_pro_explain_flow | read | Explain the execution flow of a symbol in natural language, categorizing downstream actions. |
axon_pro_file_context | read | Get full context for a specific file, including all its symbols. |
axon_pro_flow_trace | read | Trace the execution flow downstream starting from a specific symbol to understand its behavior deeply. |
axon_pro_impact_on_tests | read | Identify which tests might be affected by changing a specific symbol. |
axon_pro_list_repos | read | List all indexed repositories with their stats. |
axon_pro_related_files | read | Find files that are structurally or temporally coupled to a given file. |
axon_pro_search_code | read | Search for code patterns or literal snippets across the indexed content. |
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 (1 observation(s))
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (1)
Gates applied: no_behavioural_pass, no_license.
c98785cc109dfull audit observations/trust-audit/mcp-server/talhamsajid__axon-pro.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 |
|---|---|---|---|---|---|
| 2026-10-08 | c98785cc109d | SAFE | B | 89 | first audit |
Questions
What is the Axon Pro MCP server?
Enterprise-grade graph-powered code intelligence engine. Deep structural awareness for Laravel, PHP, Python, and JS. Powers AI agents with high-fidelity architectural context via MCP & Neo4j.
What tools does Axon Pro expose?
11 in total: 10 read-only, 1 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Axon Pro 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 Pro need?
No credential environment variables were found in its source, so it appears to need none.
How does Axon Pro run?
It speaks stdio, so it runs as a local process your client starts. It is published on PyPI as axon-pro.
How current is this page?
The grade is for one exact copy of the source (c98785cc109d), read on 2026-10-08. The repository is watched and re-audited when it changes.