mcp-garry-codes

Overview Schema Source Related Servers Discussions Admin

Search Official Garry's Mod Wiki

search_gmod_wiki

Read-onlyIdempotent

Search the official Garry's Mod Wiki by keyword or concept to discover functions, hooks, libraries, panels, and enums. Filter results by category and realm to find APIs when the exact symbol name is unknown.

Instructions

Query the official Facepunch Garry's Mod Wiki and indexed API reference by keyword or conceptual topic across functions, hooks, libraries, panels, and enums. Read-only operation with zero side effects, no authentication required, and cached offline-first execution with live documentation fallback; does NOT modify the workspace. Requires a query string. Optionally filter by category ('functions', 'hooks', 'libraries', 'panels', 'enums', 'all', default 'all'), realm ('server', 'client', 'shared', 'menu', 'all', default 'all'), and max_results (1 to 20, default 5). Use this tool for broad discovery, conceptual exploration, or finding candidate APIs when the exact symbol name is unknown. Do NOT use if you already know the exact function or hook identifier (use get_gmod_symbol instead for complete signatures, argument specifications, caveats, and official examples). Do NOT use for third-party libraries, community forum solutions, or undocumented engine quirks (use web_search_glua instead). Returns a GModToolResult envelope with status ('success' or 'failed'), summary, and data containing query, category, realm, total_matches, and an array of matching results (title, canonical wiki_url, realm, summary, signature, category).

Input Schema

TableJSON Schema

Name	Required	Description	Default
`query`	Yes	Search term, concept keyword, or partial identifier (e.g. 'net.Receive', 'PlayerInitialSpawn', 'DScrollPanel', 'draw.RoundedBox').
`realm`	No	Filter documentation by execution realm ('server', 'client', 'shared', 'menu', or 'all').	all
`category`	No	Filter search results by documentation category ('functions', 'hooks', 'libraries', 'panels', 'enums', or 'all').	all
`max_results`	No	Maximum number of documentation matches to return (integer between 1 and 20, default is 5).

Output Schema

TableJSON Schema

Name	Required	Description
`data`	Yes	Domain-specific typed payload returned by the tool.
`status`	Yes	Execution status of the tool call ('success', 'partial', 'blocked', or 'failed').
`summary`	Yes	Concise, human-readable summary of operational findings, diagnostics, or execution outcome.
`evidence`	Yes	Traceability evidence including cited documentation and generated artifacts.
`warnings`	Yes	List of non-fatal warnings, lint advisories, engine caveats, or security notices.
`nextActions`	No	Actionable, ordered recommendations for the agent's immediate next steps.

Schema Changelog

Changes observed during successful MCP inspections.

Changed6 schema fields changedSep 26, 2026

changedInput schema / properties / category / description

Previous value: -"Filter search by category"New value: +"Filter search results by documentation category ('functions', 'hooks', 'libraries', 'panels', 'enums', or 'all')."

changedInput schema / properties / max_results / description

Previous value: -"Max results to return"New value: +"Maximum number of documentation matches to return (integer between 1 and 20, default is 5)."

changedInput schema / properties / query / description

Previous value: -"Search term (e.g. 'net.Receive', 'GM:PlayerInitialSpawn')"New value: +"Search term, concept keyword, or partial identifier (e.g. 'net.Receive', 'PlayerInitialSpawn', 'DScrollPanel', 'draw.RoundedBox')."

addedInput schema / properties / query / minLength
```
Added value: +1
```

changedInput schema / properties / realm / description

Previous value: -"Filter by execution realm"New value: +"Filter documentation by execution realm ('server', 'client', 'shared', 'menu', or 'all')."

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "data": {
+      "description": "Domain-specific typed payload returned by the tool.",
+      "properties": {
+        "category": {
+          "description": "Category filter applied to search.",
+          "type": "string"
+        },
+        "query": {
+          "description": "The search query that was executed.",
+          "type": "string"
+        },
+        "realm": {
+          "description": "Realm filter applied to search.",
+          "type": "string"
+        },
+        "results": {
+          "description": "Matched Garry's Mod documentation entries with signatures and realm annotations.",
+          "items": {
+            "properties": {
+              "category": {
+                "description": "Documentation category (e.g. 'functions', 'hooks').",
+                "type": "string"
+              },
+              "realm": {
+                "description": "Execution realm affinity.",
+                "enum": [
+                  "server",
+                  "client",
+                  "shared",
+                  "menu"
+                ],
+                "type": "string"
+              },
+              "signature": {
+                "description": "Full calling signature (e.g. 'net.Receive(string messageName, function callback)').",
+                "type": "string"
+              },
+              "summary": {
+                "description": "Brief official summary of the function, hook, or panel.",
+                "type": "string"
+              },
+              "title": {
+                "description": "Symbol or article title (e.g. 'net.Receive').",
+                "type": "string"
+              },
+              "url": {
+                "description": "Canonical Facepunch Garry's Mod wiki URL.",
+                "type": "string"
+              }
+            },
+            "required": [
+              "title",
+              "url",
+              "realm",
+              "summary",
+              "signature",
+              "category"
+            ],
+            "type": "object"
+          },
+          "type": "array"
+        },
+        "total_matches": {
+          "description": "Total count of matching Garry's Mod wiki documentation entries found.",
+          "type": "integer"
+        }
+      },
+      "required": [
+        "query",
+        "category",
+        "realm",
+        "total_matches",
+        "results"
+      ],
+      "type": "object"
+    },
+    "evidence": {
+      "description": "Traceability evidence including cited documentation and generated artifacts.",
+      "properties": {
+        "artifacts": {
+          "description": "Files, packages, or manifests generated on disk or in memory.",
+          "items": {
+            "properties": {
+              "label": {
+                "description": "Descriptive label of the generated artifact.",
+                "type": "string"
+              },
+              "sha256": {
+                "description": "SHA-256 hash of the generated file.",
+                "type": "string"
+              },
+              "uri": {
+                "description": "File path or URI of the generated artifact.",
+                "type": "string"
+              }
+            },
+            "required": [
+              "label",
+              "uri"
+            ],
+            "type": "object"
+          },
+          "type": "array"
+        },
+        "inputsDigest": {
+          "description": "SHA-256 digest of normalized tool inputs for auditability.",
+          "type": "string"
+        },
+        "sources": {
+          "description": "Cited documentation, wiki pages, or external web sources supporting the result.",
+          "items": {
+            "properties": {
+              "label": {
+                "description": "Display name or title of the cited resource.",
+                "type": "string"
+              },
+              "retrievedAt": {
+                "description": "ISO-8601 timestamp of source retrieval.",
+                "type": "string"
+              },
+              "uri": {
+                "description": "Canonical URI or URL of the documentation or source.",
+                "type": "string"
+              }
+            },
+            "required": [
+              "label"
+            ],
+            "type": "object"
+          },
+          "type": "array"
+        }
+      },
+      "required": [
+        "sources",
+        "artifacts"
+      ],
+      "type": "object"
+    },
+    "nextActions": {
+      "description": "Actionable, ordered recommendations for the agent's immediate next steps.",
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "status": {
+      "description": "Execution status of the tool call ('success', 'partial', 'blocked', or 'failed').",
+      "enum": [
+        "success",
+        "partial",
+        "blocked",
+        "failed"
+      ],
+      "type": "string"
+    },
+    "summary": {
+      "description": "Concise, human-readable summary of operational findings, diagnostics, or execution outcome.",
+      "type": "string"
+    },
+    "warnings": {
+      "description": "List of non-fatal warnings, lint advisories, engine caveats, or security notices.",
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    }
+  },
+  "required": [
+    "status",
+    "summary",
+    "data",
+    "warnings",
+    "evidence"
+  ],
+  "type": "object"
+}

First observedv1.0.0Sep 24, 2026

TDQS

A4.7/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint and idempotentHint, but the description adds substantive context beyond that: no authentication required, cached offline-first execution with live fallback, and explicit confirmation that the workspace is not modified. The description aligns perfectly with the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is dense but well-organized: it leads with the core operation and safety profile, then parameters, then usage boundaries, then return envelope. Every sentence provides actionable guidance, and the 'when not to use' statements are immediate and unambiguous.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a search tool with an output schema, annotations, and clear siblings, the description covers everything an agent needs: the operation, filters, the exact conditions for choosing alternatives, behavioral guarantees, and the return envelope. There are no meaningful gaps for correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the schema already documents all four parameters, their types, defaults, constraints, and enums. The description adds a little context by framing them as optional filters and gives a clear query-example list, but it mostly restates schema information, which is acceptable but not additive.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb ('Query'), a precise resource ('official Facepunch Garry's Mod Wiki and indexed API reference'), and the scope ('functions, hooks, libraries, panels, and enums'). It clearly distinguishes this tool from siblings by positioning it as the broad-discovery search tool rather than the exact-symbol lookup or community-web-search tool.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives explicit when-to-use guidance ('broad discovery, conceptual exploration, or finding candidate APIs when the exact symbol name is unknown') and explicit when-not-to-use guidance with named alternatives: get_gmod_symbol for known identifiers and web_search_glua for third-party or community content. No inference is required.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server