Allows looking up mod information on Nexus Mods and verifying authentication via an API key.
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., "@F4 Crash Doctor Diagnose my last Fallout 4 crash"
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.
Advisory-only Fallout 4 crash diagnosis for Claude Desktop, Claude Code, or any MCP client.
When your modded Fallout 4 crashes, this tool reads the crash log, your load order, and your game setup, then explains the likely cause and fix in plain English — right inside your Claude conversation.
It is an MCP server — MCP (Model Context Protocol) is the standard way to give an AI assistant like Claude safe, well-defined abilities on your PC. This one gives Claude the ability to read your Fallout 4 crash information, nothing more.
This tool never writes, moves, deletes, or modifies any file. Ever.
It has zero tools capable of changing anything — every tool it exposes is read-only. It only looks at your crash logs, your plugin list, and your game folder, then tells you what it found.
Because it never touches your install, it works safely alongside Vortex or Mod Organizer 2. It even detects which mod manager you use, so the advice you get is phrased for your setup (e.g. "disable this in Vortex" vs "untick it in MO2's left pane").
Related MCP server: minecraft-diagnostic-mcp
Windows 10 or 11
Fallout 4 (Steam) with:
F4SE (Fallout 4 Script Extender — a loader many mods require, run via f4se_loader.exe)
Buffout 4 — the mod that actually writes crash logs when the game crashes. Without it there is nothing to diagnose. Get it here: https://www.nexusmods.com/fallout4/mods/47359
uv — a small free tool that runs Python programs without any setup on your part. One-line install in PowerShell:
winget install astral-sh.uvor, if winget isn't available:
irm https://astral.sh/uv/install.ps1 | iexYou do not need to install Python yourself — uv handles it.
Download f4-crash-doctor.mcpb from the latest release
— on the release page, click the small Assets row under the notes to expand it; the .mcpb
file is listed there (not in the release text itself). Then in Claude Desktop open
Settings → Extensions → Advanced settings and click Install Extension… — pick the
downloaded file. (Drag-and-dropping the file onto the Extensions page works on some machines, but
Windows refuses the drop with a 🚫 cursor when it doesn't know the .mcpb file type — the
Install Extension… button works everywhere.) Claude Desktop asks two optional questions
(game folder — leave empty to auto-detect; Nexus API key — skip unless you want mod lookups), and
you're done. Skip straight to First use below.
Updating from an older version: don't install over the top — Windows locks the running version's files and the install fails (EBUSY). Instead: Settings → Extensions → remove the old F4 Crash Doctor → Install Extension… with the new file → then fully restart Claude Desktop (quit from the system-tray icon, not just the window) so the new server starts. Start a new conversation after updating — an old chat will keep reasoning from the old version's answers.
Download or clone this repository somewhere permanent, e.g. C:\Tools\f4-crash-doctor.
Open a terminal (PowerShell) in that folder.
Run:
uv syncThis downloads the few libraries the tool needs. It takes a few seconds and only needs to be done once.
Open your Claude Desktop config file. It lives at:
%APPDATA%\Claude\claude_desktop_config.json(Paste that path into the File Explorer address bar. If the file doesn't exist, create it.)
Add this block (or merge f4-crash-doctor into an existing mcpServers section):
{
"mcpServers": {
"f4-crash-doctor": {
"command": "uv",
"args": ["run", "--directory", "C:\\path\\to\\f4-crash-doctor", "f4-crash-doctor"]
}
}
}Replace C:\\path\\to\\f4-crash-doctor with the real path to this folder, keeping the double backslashes (e.g. C:\\Tools\\f4-crash-doctor).
If the server never shows up in Claude (the most common setup hiccup): Claude Desktop may not find
uvright after you install it, because the updated PATH hasn't reached Claude yet. The reliable fix is to use the full path to uv.exe as the command instead of just"uv":"command": "C:\\Users\\<your-username>\\.local\\bin\\uv.exe"(That's where both installers put it. To confirm, run
where.exe uvin PowerShell.) Alternatively, sign out of Windows and back in — or reboot — so the new PATH reaches every program, and keep"command": "uv".
Restart Claude Desktop (fully quit from the system tray, then reopen).
One command:
claude mcp add f4-crash-doctor -- uv run --directory C:\path\to\f4-crash-doctor f4-crash-doctorAgain, replace the path with the real location of this folder.
After your next crash, just ask:
"Diagnose my last Fallout 4 crash."
Claude should call scan_game_environment and diagnose_crash and walk you through what happened and what to do about it.
For a guided, step-by-step diagnosis workflow, use the built-in prompt diagnose-fallout4-crash (in Claude Desktop it appears in the prompts/attachments menu once the server is connected).
Two tools (lookup_mod and check_nexus_auth) can fetch mod info from Nexus Mods, which needs a free personal API key:
Get your key from nexusmods.com → your avatar → Settings → API Keys.
Provide it one of two ways:
Create a file named .env in the repository folder containing:
NEXUS_API_KEY=your-key-hereOr add it to the Claude Desktop JSON block:
"f4-crash-doctor": {
"command": "uv",
"args": ["run", "--directory", "C:\\path\\to\\f4-crash-doctor", "f4-crash-doctor"],
"env": { "NEXUS_API_KEY": "your-key-here" }
}Everything else works without a key — only the two Nexus tools need it.
Tool | What it does |
| Lists your Buffout 4 crash logs, newest first |
| Reads and parses one crash log (newest by default) |
| Reads your plugin load order and cross-checks it against your Data folder |
| Checks game version, F4SE, Buffout 4, Address Library, and which mod manager you use |
| The full pipeline: parses the log, scans your setup, and matches known crash signatures |
| Looks up a mod on Nexus Mods (needs API key) |
| Confirms your Nexus API key works (needs API key) |
Dragging the .mcpb onto Extensions shows a 🚫 no-drop cursor — your Windows has no .mcpb
file association, so the drop (and double-clicking the file) has nowhere to go. Use
Settings → Extensions → Advanced settings → Install Extension… instead — it always works.
The server doesn't appear in Claude / never connects — almost always Claude Desktop failing to find uv. Use the full path to uv.exe as the "command" (see the note in the install section above: usually C:\\Users\\<your-username>\\.local\\bin\\uv.exe), or sign out of Windows and back in so the freshly installed uv is on every program's PATH. Also double-check the config file is valid JSON (a missing comma is enough to break it) and that you fully quit Claude Desktop from the system tray before reopening.
"No crash logs found" — Buffout 4 hasn't logged a crash yet. The folder Documents\My Games\Fallout4\F4SE\Crash Logs is only created the first time the game actually crashes with Buffout 4 installed. If the game has crashed but there's still no log, double-check Buffout 4 is installed and loading.
OneDrive moved my Documents folder — handled automatically; the tool asks Windows where your real Documents folder is. If it still looks in the wrong place, set the environment variable F4_DOCS_DIR to your Documents path (the one containing My Games).
Game installed somewhere unusual — the tool finds Steam libraries automatically, but if your Fallout 4 lives somewhere it can't find, set F4_GAME_ROOT to the folder containing Fallout4.exe.
uv sync # install dependencies (note: needs src/f4_crash_doctor present; harmless to re-run)
uv run pytest # run the test suiteSource layout: src/f4_crash_doctor/ (package), tests/ (pytest), src/f4_crash_doctor/data/ (signature knowledge pack, calibration profile, prompt kit — data, not code), packaging/ (MCPB bundle build — uv run python packaging/build_mcpb.py).
Verify the Nexus API key works and report account status.
Returns the account name, premium/supporter flags, and user id. Use this to troubleshoot lookup_mod failures. NEXUS_API_KEY is optional — only the two Nexus lookup tools need it.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses the tool's behavior (verification, reporting account status), the output fields, and an environmental dependency (NEXUS_API_KEY). It lacks detail on error handling or exact response format, but for a simple auth check this is adequate.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three concise sentences with no redundancy. The purpose is front-loaded in the first sentence, followed by return values and usage guidance. Every sentence earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with no parameters and no output schema, the description is complete: it states the purpose, lists the expected return values, clarifies the optional environment variable, and gives a direct use case. No additional context is needed for an agent to select and invoke it correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters, so the baseline is 4. The description adds meaningful context by explaining that NEXUS_API_KEY is optional and only relevant to certain tools, which goes beyond the empty schema and helps the agent understand invocation requirements.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose with specific verbs: 'Verify the Nexus API key works and report account status.' It also specifies the return values (account name, premium/supporter flags, user id), which makes it distinct from sibling tools like crash log and mod lookup tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly gives a use case: 'Use this to troubleshoot lookup_mod failures.' It also provides context about NEXUS_API_KEY being optional and only needed for Nexus lookup tools, helping the agent decide when this tool is relevant versus alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
One-shot crash diagnosis: parse log + scan environment + match signatures.
Runs the full advisory pipeline: parses the given crash log (or the
newest one when path is omitted), scans the game environment, reads
the live load order, and matches everything against the bundled crash
signature knowledge pack. Returns a compact log summary, ranked findings
(severity then confidence, each with cause, suggested user fix, and the
matched evidence lines to verify against), plus the full environment and
load-order dicts. Findings are ADVISORY ONLY — this server never changes
any file; fixes are actions for the user to take themselves.
| Name | Required | Description | Default |
|---|---|---|---|
| path | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description takes full responsibility for behavioral disclosure. It explicitly states that it 'never changes any file', that findings are 'ADVISORY ONLY', and details the exact output structure (ranked findings, evidence lines, environment and load-order dicts). It also discloses the default behavior when path is omitted.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is structured with a lead phrase followed by a clear breakdown of pipeline steps and outputs. It's about 100 words, which is appropriate for a tool that orchestrates multiple subsystems. Every sentence adds useful information, though a slight tightening could push it to 5.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given that there is no output schema and no annotations, the description covers all required aspects: what it does, what it returns (including ranking criteria), what is safe (no file changes), and how the optional parameter behaves. It is fully complete for an orchestration tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The only parameter `path` is not described in the schema (coverage 0%), so the description's clarification that it parses the given log or defaults to the newest one fully compensates. This is the key semantic information the agent needs to invoke the tool correctly.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description opens with 'One-shot crash diagnosis: parse log + scan environment + match signatures' which clearly states the tool's action and scope. It distinguishes from sibling tools by describing the full pipeline, not just individual steps like list_crash_logs or get_load_order.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explains the comprehensive nature of this tool versus the individual sibling tools, and clarifies that it can use an explicit path or default to the newest log. However, it doesn't explicitly say when to use it instead of the simpler tools, such as 'if you only need a single file, use get_crash_log'. That nuance prevents a 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Parse a Buffout 4 crash log into structured sections.
With no path, parses the NEWEST crash log found in the standard
folders; pass an absolute path (e.g. from list_crash_logs) to parse a
specific one. Explicit paths must be crash logs: either inside the
standard crash-log folders or named crash-*.log — anything else is
refused with an error. Returns the exception (type, address, faulting module),
probable call stack, F4SE plugin list, plugin load order as logged,
modules, settings, and any parse warnings. The raw STACK dump is
truncated to 50 lines to keep responses small. Returns
{"error": "no crash logs found", "searched_dirs": [...]} when there is
nothing to parse.
| Name | Required | Description | Default |
|---|---|---|---|
| path | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description fully carries the transparency burden. It discloses default behavior (newest log), refusal conditions for invalid paths, the specific return fields (exception, call stack, plugin list, etc.), the stack truncation to 50 lines, and the exact error payload when no logs are found. This is exceptionally transparent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is appropriately sized and well-structured. It opens with a one-sentence purpose, followed by path behavior, validation constraints, return contents, truncation notice, and error case. Every sentence carries essential information without redundancy or fluff.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (parses crash logs into multiple sections) and the absence of an output schema, the description thoroughly covers return values, error handling, and edge cases. It also hints at integration with list_crash_logs, making it complete for an AI agent to invoke correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The only parameter, 'path', has a schema that just says string/null with a default. The description adds deep semantic meaning: what happens when omitted (newest log), how to specify a particular log (from list_crash_logs), and validation rules (must be inside crash-log folders or named crash-*.log). This fully compensates for the 0% schema description coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's function: 'Parse a Buffout 4 crash log into structured sections.' It uses a specific verb ('parse'), specifies the resource ('Buffout 4 crash log'), and indicates the output format ('structured sections'). This distinguishes it from siblings like list_crash_logs, which lists logs, and diagnose_crash, which presumably analyzes causes.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear usage context: without a path it automatically selects the newest log, and with an explicit path it parses that specific log. It also gives constraints (paths must be crash logs) and references list_crash_logs as a source for paths. It does not explicitly compare with other siblings like diagnose_crash, but the context is clear enough for typical use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Read the live Fallout 4 load order and cross-check it against Data.
Parses %LOCALAPPDATA%\Fallout4\Plugins.txt ('*' prefix = enabled) and lists the .esm/.esp/.esl files actually present in the game's Data folder. Reports both mismatch directions: enabled plugins whose file is missing from Data (a classic missing-master crash cause) and files in Data that are not in the load order. Implicitly loaded plugins (Fallout4.esm, official DLC, Creation Club content) are never listed in Plugins.txt and are excluded from the mismatch lists. When Mod Organizer 2 manages the game, the on-disk Plugins.txt is NOT the real load order (MO2 virtualizes it): plugins_txt_reliable is false, the cross-check is skipped, and a warning explains why. Read-only.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and excels: it details parsing of Plugins.txt, the '*' prefix, Data folder listing, both mismatch directions, exclusion of implicit plugins, MO2 handling with a reliability flag, and explicitly states 'Read-only'. This is rich behavioral disclosure beyond the tool's name.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is moderately long but every sentence adds value: it front-loads the main purpose, then systematically explains the parsing logic, mismatch reporting, implicit plugin exclusions, MO2 caveat, and safety. No fluff or redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity, zero parameters, and lack of output schema, the description is remarkably complete. It covers all edge cases (missing files, extra files, implicit plugins, MO2 virtualization) and clearly defines the tool's behavior in each scenario, leaving no significant ambiguity for the agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters, so the baseline is 4. The description does not need to add parameter semantics, and it sufficiently explains the tool's operation without referencing parameters.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool reads the live Fallout 4 load order and cross-checks it against Data, which is a specific verb+resource+scope. It differentiates from sibling tools by focusing on load order integrity, distinct from crash logs, environment scans, or diagnostics.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies when to use (to investigate load order mismatches causing missing-master crashes) and explicitly mentions a caveat for MO2 users, stating the cross-check is skipped. However, it does not explicitly name alternative tools or provide a direct 'use this when' statement.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List Buffout 4 crash logs on this machine, newest first.
Searches the standard Fallout 4 crash-log folders under the user's
Documents directory (override with the F4_DOCS_DIR environment variable).
Returns up to limit entries with absolute path, last-modified timestamp
(ISO 8601) and size in KB, plus the directories that were searched.
Read-only: nothing is opened or modified.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full transparency burden. It explicitly states it is read-only and does not open or modify anything, and it discloses the environment variable override. It does not mention error handling or potential side effects beyond the read-only claim, but for a listing tool this is sufficient.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is three sentences, front-loaded with the core purpose, then provides search location, return details, and side-effect disclosure. Every sentence earns its place with no redundancy or filler.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (one optional parameter, no output schema, no annotations), the description covers all essential aspects: what, where, ordering, return fields, directories searched, and read-only behavior. It adequately informs an agent of the full behavior without needing an output schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
There is one parameter (limit) with 0% schema description coverage. The description adds meaning by explaining that it returns up to `limit` entries, which is essential and not provided elsewhere. It also mentions an environment variable not part of the schema. The description could also note the default behavior (default 10) explicitly, but it is present in the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly specifies the action (list), the resource (Buffout 4 crash logs), and the scope (on this machine, newest first). It is distinct from sibling tools like get_crash_log, which likely retrieves a single log's content.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear context for when to use this tool: to list crash logs on the machine. It implies use before fetching a specific log, but does not explicitly name alternatives or exclusions. The sibling tool names hint at alternatives, but the description itself could be more explicit about when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Look up a mod on Nexus Mods (read-only; requires NEXUS_API_KEY).
Accepts a Nexus URL (https://www.nexusmods.com/fallout4/mods/47359) or 'game/mod_id' (e.g. 'fallout4/47359'). Returns mod metadata (name, version, author, summary) and the available files with versions and upload dates — useful for checking whether a suspect mod has a newer version or a compatibility patch. Never downloads anything. Without NEXUS_API_KEY this returns an error explaining that mod lookups are optional; every other tool still works.
| Name | Required | Description | Default |
|---|---|---|---|
| url_or_id | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description fully carries the burden. It discloses read-only status, the NEXUS_API_KEY requirement, that it never downloads anything, and the exact error behavior without the key. This is exceptional transparency for a tool with no annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is appropriately sized for the tool's complexity. It front-loads the core purpose, then adds input format, return data, use case, and error behavior without redundancy. Every sentence adds value and the structure is easy to scan.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the low complexity (one parameter, no output schema), the description is complete. It covers input formats, return contents, authentication requirements, safety (no downloads), and fallback behavior when the key is missing. No gaps remain for the agent to infer.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0%, and the single parameter url_or_id has no schema description. The description fully compensates by explaining the accepted formats (Nexus URL or 'game/mod_id') and providing a concrete example, adding meaning far beyond the raw schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's function: 'Look up a mod on Nexus Mods' with a specific verb and resource. It distinguishes itself from siblings like list_crash_logs or scan_game_environment by focusing on Nexus Mod metadata lookup.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear context for when to use the tool: 'useful for checking whether a suspect mod has a newer version or a compatibility patch.' It does not explicitly name alternative tools or exclusion criteria, but the use case is well implied and distinct from siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Scan the installed Fallout 4 for versions, F4SE health, and mod managers.
Discovers the game root (F4_GAME_ROOT env var, known locations, then all Steam libraries), then reports: game exe version, F4SE loader/DLL version, Address Library presence and whether it matches the game version, Buffout 4 variant + version, a crash_logging report (which DLLs write crash logs; a recognized_bundle means those DLLs ship together as ONE mod — e.g. Buffout 4 AE + CrashLoggerAE — and are NOT rival loggers; trust its notes over pattern-matched folklore), all F4SE plugin DLLs, BA2 archive count, crash-log folders, and which mod manager is in use (MO2 / Vortex / manual / unknown). Call this FIRST in any diagnosis session — version mismatches here explain many crashes before the log is even read. Read-only.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Despite having no annotations, the description is highly transparent: it states it is read-only, describes the discovery order (env var, known locations, Steam libraries), lists all reported data points, and explains the nuanced 'recognized_bundle' interpretation for crash loggers. This surpasses basic behavioral disclosure.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is dense but well-structured: a one-sentence summary, discovery details, a comprehensive report list, and usage guidance. Every sentence contributes meaningful value, and the length is appropriate for the tool's complexity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no annotations and no output schema, the description carries the full burden. It fully specifies what the scan discovers (game version, F4SE health, mod managers, etc.) and includes a subtle interpretation rule (recognized_bundle) that prevents misuse. This is as complete as expected for a complex diagnostic tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool takes zero parameters, so the baseline is 4. There is no schema to add detail, and the description clarifies that the scan is fully automatic with no user input required.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states that the tool scans the installed Fallout 4 for versions, F4SE health, and mod managers, and enumerates the specific outputs. It distinguishes itself from sibling tools by being the initial comprehensive scan in a diagnosis session.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It explicitly instructs to call this tool FIRST in any diagnosis session and explains why (version mismatches explain many crashes before reading logs). It does not name alternative tools or provide when-not guidance, but the context is clear and actionable.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v0.1.1check_nexus_authdiagnose_crashget_crash_logget_load_orderlist_crash_logslookup_modscan_game_environmentEach tool has a clearly distinct purpose: listing logs, parsing logs, reading load order, scanning environment, running combined diagnosis, looking up mods, and checking auth. No two tools overlap in function.
All tool names follow a consistent verb_noun pattern (list_crash_logs, get_crash_log, get_load_order, scan_game_environment, diagnose_crash, lookup_mod, check_nexus_auth), all lowercase with underscores.
Seven tools is well-scoped for a crash diagnosis server: the core operations (list, parse, scan, diagnose) plus two optional Nexus helpers and one auth check. No superfluous tools.
The tool surface covers the full diagnosis workflow: discovering logs, parsing them, checking the environment and load order, and combining everything into ranked findings. The optional mod lookup and auth check fill the remaining practical need without dead ends.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Analytics and debugging for your MCP server — explore usage and sessions, then root-cause errors.
DBRE-grade SQL analysis inside any MCP client. No connection. No install. Paste a query.
A paid remote MCP for ClawManager, built to return verdicts, receipts, usage logs, and audit-ready J
Security scanner for MCP servers. Detect vulnerabilities, prompt injection, and tool poisoning.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Apocalypse-Meow/f4-crash-doctor'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
