mw_diagnose_crash
Crash log in, culprit shortlist out. Parses the log, then correlates its suspects with the loaded plugins and (with a gameId) the known-conflict database into one bundle: which suspected mods are actually in the load order, at what index, and which loaded plugins have known conflicts. It lines up...
This record as markdown: /tools/171county-modwrench/mw-diagnose-crash.md
What mw_diagnose_crash does on ModWrench MCP Server
AI agents call mw_diagnose_crash to retrieve information from ModWrench MCP Server without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
gameId | string | — | Canonical game id (e.g. 'skyrimspecialedition', 'fallout4') to include the known-conflict cross-check. Omit to skip it. |
logPath | string | — | Absolute path to a crashlog on disk (the SKSE/F4SE crash folder, or the game's BepInEx/LogOutput.log). |
logType | string | — | Format hint. Default 'auto' — detect from content. |
logContent | string | — | Crashlog content as a string. Provide this OR logPath. |
Parameters from the server's own tool schema.
Why mw_diagnose_crash is rated Low
Even though mw_diagnose_crash only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
The rule that runs mw_diagnose_crash safely
PolicyLayer is an MCP gateway: it sits between your AI agents and ModWrench MCP Server, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For mw_diagnose_crash, this is the rule to start with:
mw_diagnose_crash is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect ModWrench MCP Server, apply this rule, and every mw_diagnose_crash call is checked against it from then on.
Questions about mw_diagnose_crash
Crash log in, culprit shortlist out. Parses the log, then correlates its suspects with the loaded plugins and (with a gameId) the known-conflict database into one bundle: which suspected mods are actually in the load order, at what index, and which loaded plugins have known conflicts. It lines up the evidence; it does NOT name the cause — that's the model's call, reasoned over the data. Use when the user says "what's causing my crash", "which mod is it", or pastes a crash log and wants the answer. It is categorised as a Read tool in the ModWrench MCP Server MCP Server, which means it retrieves data without modifying state.
mw_diagnose_crash accepts 4 parameters: gameId, logPath, logType, logContent. The full parameter table on this page comes from the server's own tool schema.
Register the ModWrench MCP Server MCP server in PolicyLayer and add a rule for mw_diagnose_crash: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches ModWrench MCP Server. Nothing to install.
mw_diagnose_crash is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the mw_diagnose_crash rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for mw_diagnose_crash. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
mw_diagnose_crash is provided by the ModWrench MCP Server MCP server (@modwrench/cli). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on ModWrench MCP Server, and thousands of servers like it.
This server
Across the catalogue