TROUBLESHOOTING

A troubleshooting guide for Axom MCP, a system that connects coding agents to Axom tools and rules. It lists common setup problems and their checks.

In plain words
What is it for?
Use it to troubleshoot Axom MCP configuration, verify commands and server settings, and understand how Axom rules work in editors such as Zed and Cursor.
Why use it?
It helps explain missing tools, startup timeouts, and editor limitations instead of leaving you to diagnose them from scratch.

Agent

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/pugzui/axom/troubleshooting
Clone the repo
git clone --depth 1 https://github.com/PugzUI/axom
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 739 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00739
Opus 5 $0.00000 $0.00369
Sonnet 5 $0.00000 $0.00148
Haiku 4.5 $0.00000 $0.00074

Measured yesterday against content hash 651b6e10e82d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

TROUBLESHOOTING scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

docs/agents/TROUBLESHOOTING.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Axom Agent Troubleshooting Guide

Common issues and solutions for Axom MCP.

Agent Limitations

Zed

Zed does not support global rules or skills. Zed only supports:

  • Project-level rules: .rules, AGENTS.md, .cursorrules, etc. in project root
  • Rules Library: Internal database (no CLI/API to inject rules)

For Zed, only MCP configuration is installed. To use Axom rules:

  1. Copy AGENTS.md to your project root, OR
  2. Manually add rules via Zed's Rules Library (cmd-alt-l)

Quick Diagnostics

Tool Not Found

Error: Tool axom_mcp_* not found

Solutions:

  1. Check prefixed variants: axom-mcp-server_axom_mcp_*.
  2. Verify Axom MCP is configured in your client.
  3. Check server logs for startup errors.

Context Server Timeout

Error: axom context server failed to start: Context server request timeout

Common causes:

  • Client MCP config still points to a stale command (for example old uvx entries).
  • axom-mcp not installed in the current Python environment.

Checks:

  1. Re-run install from the repo root: make install.
  2. Confirm command exists: command -v axom-mcp.
  3. For Cursor, verify ~/.cursor/mcp.json uses:
    • mcpServers.axom.command = "axom-mcp" (args optional, omit if empty)
  4. Restart the IDE/client after config changes.

Chain Execution Failed

Error: Chain stops unexpectedly or variables not resolved.

Common causes:

  • Using ${content} instead of ${_result}.
  • Missing condition in chain step.
  • Tool name typo.
  • Invalid JSON syntax.

Memory Not Stored

Error: Write succeeds but memory not found.

Checklist:

  • action is "write".
  • name follows [type]_[descriptor]_[YYYYMMDD].
  • importance and memory_type are valid.
  • Database connection is active.

Permission Denied

Error: Cannot read/write files or execute commands.

Solutions:

  1. File ops: Use absolute paths.
  2. Shell: Ensure non-interactive.
  3. Location: Use axom_mcp_exec with operation: "list" to verify.

Read the full file on GitHub · 99 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 99 lines · 0 tokens per session scan A 651b6e10e82d

Subscribe to this mod's changes

TROUBLESHOOTING is an agent published in the GitHub repository PugzUI/axom (1 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 739 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.