lynx-mcp

Overview Schema Source Related Servers Discussions Admin

search

Read-onlyIdempotent

Find code and documentation by describing functionality in plain words. Returns ranked matches with file:line references and relevance scores, with optional filters for source, path, or file type.

Instructions

Hybrid semantic + lexical search over the indexed code and docs. Describe what the code does in plain words ('method that clamps camera zoom'), not an identifier. Returns ranked chunks with file:line, symbol and score; a hybrid score near 0.03 is a strong match. Omit source to search every source at once. outline=true returns signatures only, for cheap triage of broad queries.

Input Schema

TableJSON Schema

Name	Required	Description
`query`	Yes	What the code does, in plain words, not an identifier.
`top_k`	No	Max results; default from config.
`source`	No	Source name, list of names, or omit for all sources, fused.
`outline`	No	Signatures only, no bodies: cheap triage for broad queries.
`file_glob`	No	Restrict to paths matching this glob, e.g. `*.cs`.
`extensions`	No	Restrict to these extensions, e.g. ['.cs'].
`path_contains`	No	Restrict to paths containing this substring.

Schema Changelog

Changes observed during successful MCP inspections.

Changed17 schema fields changedv1.9.0Sep 6, 2026

changedInput schema / properties / extensions / description

Previous value: -"Restrict results to these file extensions, e.g. `['.cs', '.shader']`."New value: +"Restrict to these extensions, e.g. ['.cs']."

removedInput schema / properties / extensions / title
```
Removed value: -"Extensions"
```

changedInput schema / properties / file_glob / description

Previous value: -"fnmatch glob to restrict results by path/filename, e.g. `*.cs` or `**/Editor/*`."New value: +"Restrict to paths matching this glob, e.g. `*.cs`."

removedInput schema / properties / file_glob / title
```
Removed value: -"File Glob"
```

changedInput schema / properties / outline / description

Previous value: -"If true, return each hit's signature + first doc line instead of its full body — cheap triage for broad queries or a large top_k. Scan the signatures, then read the one body you need (find_definition, or its file:line). Default false = full bodies, for when you'll use the code right away."New value: +"Signatures only, no bodies: cheap triage for broad queries."

removedInput schema / properties / outline / title
```
Removed value: -"Outline"
```

changedInput schema / properties / path_contains / description

Previous value: -"Keep only results whose file path contains this substring."New value: +"Restrict to paths containing this substring."

removedInput schema / properties / path_contains / title
```
Removed value: -"Path Contains"
```

changedInput schema / properties / query / description

Previous value: -"Natural-language description of the behavior to find (e.g. 'method that handles player damage calculation'), NOT an identifier — use grep for exact names."New value: +"What the code does, in plain words, not an identifier."

removedInput schema / properties / query / title
```
Removed value: -"Query"
```

changedInput schema / properties / source / anyOf

Previous value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "type": "string"
+  },
+  {
+    "items": {
+      "type": "string"
+    },
+    "type": "array"
+  },
+  {
+    "type": "null"
+  }
+]

changedInput schema / properties / source / description

Previous value: -"Source name from `list_sources`. Omit to use the default: all sources for `search`/`deep_search` (RRF-fused), or the single applicable source for the others."New value: +"Source name, list of names, or omit for all sources, fused."

removedInput schema / properties / source / title
```
Removed value: -"Source"
```

changedInput schema / properties / top_k / description

Previous value: -"Maximum number of results to return. Defaults to the server's configured value."New value: +"Max results; default from config."

removedInput schema / properties / top_k / title
```
Removed value: -"Top K"
```
removedInput schema / title
```
Removed value: -"_searchArguments"
```

changedOutput schema / (root)

Previous value: -{
-  "properties": {
-    "result": {
-      "title": "Result",
-      "type": "string"
-    }
-  },
-  "required": [
-    "result"
-  ],
-  "title": "_searchOutput",
-  "type": "object"
-}New value: +null

Changed1 schema field changedv1.7.0Jun 19, 2026

addedInput schema / properties / outline

Added value: +{
+  "default": false,
+  "description": "If true, return each hit's signature + first doc line instead of its full body — cheap triage for broad queries or a large top_k. Scan the signatures, then read the one body you need (find_definition, or its file:line). Default false = full bodies, for when you'll use the code right away.",
+  "title": "Outline",
+  "type": "boolean"
+}

First observedv1.5.1Jun 15, 2026

TDQS

A4.5/5.0

Behavior4/5

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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, destructiveHint false), so the bar is lower, and the description clears it by adding genuinely useful behavior: return format (ranked chunks with file:line, symbol, score), score interpretation (0.03 ≈ strong match), and mode behavior for outline. No contradiction with 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?

Four sentences, each earning its place: scope, query phrasing, return format plus score calibration, then two parameter tips. The most important usage constraint (plain-words query) is front-loaded in the second sentence. Zero filler.

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 7-parameter tool with no output schema and 15 siblings, this description covers the critical gaps: what the tool returns, how to judge result quality, how to phrase input, and how two key parameters change behavior. Filtering params (file_glob, extensions, path_contains) are self-explanatory from the schema, so nothing an agent needs to call it correctly is missing.

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

Parameters4/5

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

Schema coverage is 100%, so baseline is 3. The description adds value on top by specifying how to phrase `query`, the fusion behavior when `source` is omitted, and the triage use of `outline=true` — going beyond the schema's terse descriptions rather than simply repeating them.

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?

States a specific verb and resource — 'Hybrid semantic + lexical search over the indexed code and docs' — plus the distinct query contract ('describe what the code does in plain words, not an identifier'). This differentiates it from sibling symbol-oriented tools like find_definition, find_usages, and describe_symbol, and from deep_search, without needing to inspect any of them.

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

Usage Guidelines4/5

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

Gives strong practical context: query phrasing rules, omitting `source` to search everything, and outline=true for cheap broad triage. However, it never names sibling alternatives or states explicit when-not-to-use conditions, so an agent must infer the boundary with find_similar/deep_search from the plain-words contract alone.

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

Deploy Server

search

Instructions

Input Schema

Schema Changelog

TDQS

Other Tools