How do I use rev-eng-cursor-regex-mcp?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@rev-eng-cursor-regex-mcp search for 'async function' in the codebase" 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.

rev-eng-cursor-regex-mcp

by blas0

Overview Schema Related Servers Score Discussions

TypeScript

rev-eng-cursor-regex-mcp

rev-eng-cursor-regex-mcp is a portable TypeScript Model Context Protocol server for fast literal and regex search over local workspaces. It uses a sparse n-gram index for candidate pruning, then performs deterministic verification against the real file contents.

Features

index.ensure, index.status, and index.clear for local index lifecycle management
Automatic .gitignore bootstrap for the local .rev-eng-cursor-regex-mcp/ cache when that cache lives inside the workspace
search.literal for exact-string search
search.regex for ECMAScript regex search with sparse n-gram planning
query.explain for anchor extraction and fallback analysis
document.inspect_terms for trigram, masked-trigram, and sparse-term diagnostics
Static resources for algorithm notes, storage layout, and agent workflow guidance
Reusable prompts for investigation flow and regex refinement
stdio and Streamable HTTP entrypoints

Related MCP server: File Search MCP

Requirements

Node.js 20 or newer

Quick Start From Source

npm install
npm run build
npm run start:stdio

This starts the MCP server over stdio from a fresh clone with no global install required.

Run Modes

Run over stdio from a local clone:

npm run start:stdio

Run over Streamable HTTP from a local clone:

npm run start:http

Run the built CLI directly:

node dist/cli.js stdio
node dist/cli.js http --host 127.0.0.1 --port 3333

Run without cloning after the package is published:

npx rev-eng-cursor-regex-mcp stdio
npx rev-eng-cursor-regex-mcp http --host 127.0.0.1 --port 3333

Environment

REV_ENG_CURSOR_REGEX_MCP_WORKSPACE_ROOT: default workspace root
REV_ENG_CURSOR_REGEX_MCP_INDEX_DIR: parent directory where .rev-eng-cursor-regex-mcp/ is created
REV_ENG_CURSOR_REGEX_MCP_BOOTSTRAP_GITIGNORE: when set to false, 0, off, or no, skip automatic .gitignore bootstrapping
REV_ENG_CURSOR_REGEX_MCP_HTTP_HOST: default HTTP bind host
REV_ENG_CURSOR_REGEX_MCP_HTTP_PORT: default HTTP bind port

Verify A Fresh Clone

npm install
npm run typecheck
npm test
npm run build

Claude Desktop Example

{
  "mcpServers": {
    "rev-eng-cursor-regex-mcp": {
      "command": "node",
      "args": [
        "/absolute/path/to/rev-eng-cursor-regex-mcp/dist/cli.js",
        "stdio"
      ]
    }
  }
}

Notes

Git workspaces use a commit-keyed base index plus a mutable overlay for working-tree changes.
index.ensure adds the cache directory to .gitignore automatically when the cache root lives inside the workspace. Pass bootstrapGitignore: false or set REV_ENG_CURSOR_REGEX_MCP_BOOTSTRAP_GITIGNORE=false to opt out.
Non-git workspaces fall back to snapshot mode with .gitignore-style filtering.
Ignore-case regex searches fall back to a deterministic full scan because the sparse index is case-sensitive.

Available Tools

8 tools

document.inspect_termsInspect TermsA

Read-only

Show the trigrams or sparse n-grams that would be emitted for a file or text snippet, including offsets and rarity weights.

ParametersJSON Schema

Name	Required	Description
`mode`	Yes	Choose the tokenization mode to inspect.
`path`	No	Absolute path to the source file to inspect.
`text`	No	Inline text snippet to inspect instead of reading a file.
`maxTerms`	No	Maximum number of emitted terms to return. Defaults to 256.

Output Schema

ParametersJSON Schema

Name	Required	Description
`mode`	Yes
`notes`	Yes
`terms`	Yes
`termCount`	Yes

TDQS

A4/5.0

Behavior4/5

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

The description adds context beyond annotations by specifying the output includes offsets and rarity weights and that the tool simulates emission. It is consistent with readOnlyHint. Could improve by clarifying if an index is required.

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?

Single sentence, no wasted words, clearly front-loaded with the key action.

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

Completeness4/5

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

Given the output schema exists and the description covers the tool's purpose and outputs, it is largely complete. Minor gap: no mention of maxTerms default behavior.

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 description coverage is 100%, so description need not add parameter details. It does not elaborate on any parameters, so baseline 3 is appropriate.

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 specifies the verb 'Show', the resource 'trigrams or sparse n-grams', and the context 'for a file or text snippet, including offsets and rarity weights'. It clearly differentiates from sibling tools which focus on indexing and search.

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

Usage Guidelines3/5

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

The description implicitly states usage (to inspect tokenization output) but does not provide explicit guidance on when to use versus alternatives, nor does it mention any prerequisites or exclusions.

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

index.clearClear IndexA

Destructive

Delete cached index data for a workspace. Use this only to recover from stale or corrupt local index state.

ParametersJSON Schema

Name	Required	Description	Default
`scope`	Yes	Choose `overlay` to drop only the mutable layer or `all` to remove the entire local cache.
`workspaceRoot`	No	Absolute workspace root whose cache should be cleared. Defaults to the server workspace.

Output Schema

ParametersJSON Schema

Name	Required	Description
`elapsedMs`	Yes
`storageDir`	Yes
`clearedScope`	Yes
`removedPaths`	Yes

TDQS

A4.3/5.0

Behavior4/5

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

Annotations already declare destructiveHint: true, so description's disclosure of deletion is consistent. Adds context about what is deleted (cached data) and the conditions (stale/corrupt state), going beyond the annotation flag.

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?

Two tight sentences with no wasted words. The action and purpose are front-loaded, and every sentence serves a clear function: stating the operation and when to use it.

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?

Given the simple destructive action, the description is fully sufficient. Annotations cover safety context, schema covers parameters, and an output schema exists for return values. No further context needed.

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 description coverage is 100% and the schema already provides clear descriptions for both parameters (scope enum and workspaceRoot). The description adds no additional parameter-level meaning, so baseline 3 is appropriate.

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?

Clearly states the verb 'delete' and resource 'cached index data' for a workspace. Provides specific use case ('recover from stale or corrupt local index state') which distinguishes it from sibling tools like index.ensure or index.status.

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?

Explicitly says 'Use this only to recover from stale or corrupt local index state' which gives clear context. Lacks explicit exclusions or alternatives, but the conditional is strong enough to guide appropriate use.

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

index.ensureEnsure IndexA

Idempotent

Build or refresh the local regex index for a workspace and return the active base revision plus overlay state.

ParametersJSON Schema

Name	Required	Description
`excludeGlobs`	No	Glob patterns that should be excluded before indexing.
`forceRebuild`	No	Rebuild the immutable base index even when the active revision already exists.
`includeGlobs`	No	Glob patterns that define which files belong to the corpus. Defaults to `*/`.
`workspaceRoot`	No	Absolute workspace root to index. Defaults to the server workspace.
`refreshOverlay`	No	Refresh the writable overlay after resolving the base index. Defaults to true.
`bootstrapGitignore`	No	When true, add the cache directory to the workspace .gitignore if the cache lives inside the workspace. Defaults to true.

Output Schema

ParametersJSON Schema

Name	Required	Description
`elapsedMs`	Yes
`sourceMode`	Yes
`storageDir`	Yes
`baseIndexId`	Yes
`workspaceId`	Yes
`gitignorePath`	Yes
`gitignoreEntry`	Yes
`sourceRevision`	Yes
`overlayRevision`	Yes
`gitignoreUpdated`	Yes
`overlayFileCount`	Yes
`trackedFileCount`	Yes

TDQS

A4/5.0

Behavior4/5

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

Annotations declare idempotentHint=true and openWorldHint=false. The description complements by explaining the build/refresh process and the return value. It does not contradict annotations and adds context about the index state. However, it could mention potential side effects like disk usage or time consumption.

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 a single sentence that is front-loaded with the action and outcome. Every word is necessary, and it avoids redundancy.

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

Completeness4/5

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

Given the tool's complexity (6 optional parameters, output schema exists), the description covers the core purpose and return value. However, it lacks context on when to use parameters like forceRebuild vs refreshOverlay, and could mention performance implications. The annotation partially compensates.

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 description coverage is 100%, so each parameter is documented in the schema. The tool description does not add extra meaning beyond what the schema provides. The baseline for high coverage is 3.

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 clearly states the verb 'Build or refresh' and the resource 'local regex index', and specifies the output 'return the active base revision plus overlay state'. This distinguishes it from sibling tools like index.status (status check) and search.* (search operations).

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

Usage Guidelines3/5

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

The description implies when to use the tool (when an index needs to be built or refreshed) but does not provide explicit guidance on when not to use it or alternatives. There is no mention of prerequisites or comparison with sibling tools like index.status or index.clear.

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

index.statusIndex StatusA

Read-only

Describe the active regex index for a workspace, including corpus selection, freshness, and storage paths, without rebuilding it.

ParametersJSON Schema

Name	Required	Description	Default
`workspaceRoot`	No	Absolute workspace root to inspect. Defaults to the server workspace.

Output Schema

ParametersJSON Schema

Name	Required	Description
`ready`	Yes
`byteSize`	Yes
`fileCount`	Yes
`sourceMode`	No
`stalePaths`	Yes
`storageDir`	Yes
`workspaceId`	Yes
`sourceRevision`	No
`overlayFileCount`	Yes

TDQS

A4.2/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true; description adds value by specifying what is described (corpus, freshness, storage paths) and the non-destructive nature ('without rebuilding it'), providing useful behavioral context.

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?

Single sentence, 13 words, front-loaded with the main action and details, no wasted words.

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

Completeness4/5

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

Given the presence of an output schema (not shown), the description adequately covers the tool's purpose and key details. Could briefly clarify what 'active regex index' means, but overall sufficient for a simple stateless inspection tool.

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 description coverage is 100% for the single parameter, and the description does not add significant meaning beyond the schema's existing description. Baseline of 3 is appropriate.

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?

Describes the tool as 'Describe the active regex index for a workspace' with specific details (corpus selection, freshness, storage paths) and distinguishes from siblings like index.ensure by adding 'without rebuilding it'.

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?

Clearly states the context ('for a workspace') and implies it is for inspection, but lacks explicit guidance on when not to use or alternatives beyond the list of sibling tools.

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

query.explainExplain Query PlanA

Read-only

Explain how the server will decompose a query, what anchors it can extract, and whether the search will fall back to a full scan.

ParametersJSON Schema

Name	Required	Description	Default
`flags`	No	Optional ECMAScript regex flags.
`pattern`	Yes	ECMAScript regular expression source without surrounding slashes.

Output Schema

ParametersJSON Schema

Name	Required	Description
`valid`	Yes
`plannerMode`	Yes
`branchAnchors`	Yes
`fallbackReason`	No
`classicTrigrams`	Yes
`recommendedTool`	Yes
`requiresFullScan`	Yes
`normalizedPattern`	Yes
`skippedConstructs`	Yes
`extractableAnchors`	Yes
`alternationBranches`	Yes
`sparseCoveringTerms`	Yes

TDQS

A4.1/5.0

Behavior4/5

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

Beyond the readOnlyHint and openWorldHint annotations, the description discloses that the tool explains decomposition, extraction of anchors, and fallback to full scans, providing useful behavioral context.

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 a single, front-loaded sentence that clearly communicates the tool's purpose with no wasted words.

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?

Given the presence of an output schema (context signals indicate has output schema: true), the description adequately explains what the tool reveals (decomposition, anchors, scan fallback), providing sufficient context.

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 description does not need to add parameter details. The description focuses on the output and adds context, but does not enhance parameter understanding beyond the schema.

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 uses specific verbs ('explain', 'decompose', 'extract') and clearly identifies the resource (query plan). It distinguishes from sibling tools like search.literal, search.regex, and search.plan by focusing on query decomposition and anchor extraction.

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

Usage Guidelines3/5

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

The description implies when to use it (to understand query decomposition), but does not explicitly state when not to use it or offer alternatives such as search.plan for other plan-related tasks.

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

search.literalSearch LiteralA

Read-only

Find exact text in indexed workspace files. Prefer this over regex when you already know the exact string.

ParametersJSON Schema

Name	Required	Description
`needle`	Yes	Exact text to search for without any regex syntax.
`pathGlobs`	No	Optional relative glob patterns that narrow the search to specific folders or files.
`afterLines`	No	Number of context lines to include after each match. Defaults to 1.
`maxResults`	No	Maximum number of matches to return. Defaults to 100.
`beforeLines`	No	Number of context lines to include before each match. Defaults to 1.
`caseSensitive`	No	Set to false to perform a case-insensitive full-text match.
`workspaceRoot`	No	Absolute workspace root to search. Defaults to the server workspace.
`autoEnsureIndex`	No	Refresh the local index automatically before searching. Defaults to true.

Output Schema

ParametersJSON Schema

Name	Required	Description
`plan`	No
`matches`	Yes
`elapsedMs`	Yes
`queryKind`	Yes
`truncated`	Yes
`matchCount`	Yes
`plannerMode`	No
`fallbackReason`	No
`scannedDocCount`	Yes
`candidateDocCount`	Yes
`coveringGramCount`	No
`extractableAnchors`	No

TDQS

A4.2/5.0

Behavior3/5

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

Annotations provide readOnlyHint and openWorldHint, so safety is clear. The description adds 'indexed workspace files' context but does not elaborate on pagination, performance, or other behaviors beyond what annotations cover.

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?

Two sentences that convey purpose and usage guidance with zero wasted words. Perfectly sized and front-loaded.

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

Completeness4/5

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

Given the 8 parameters, existing output schema, and annotations, the description covers essential purpose and usage. It could add more about interaction with index tools or autoEnsureIndex behavior, but overall it's sufficiently complete.

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 baseline is 3. The description provides no parameter-specific details beyond what the schema already documents.

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 'Find exact text in indexed workspace files' with a specific verb ('Find') and resource ('exact text in indexed workspace files'). It also distinguishes from sibling 'search.regex' by advising preference when exact string is known.

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 explicitly advises 'Prefer this over regex when you already know the exact string', giving clear when-to-use guidance and naming the alternative (regex).

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

search.planPlan Search WorkflowA

Read-only

Plan the MCP-first search workflow for an exploratory objective and recommend whether to ensure the index, use literal search, explain a regex, or run regex search.

ParametersJSON Schema

Name	Required	Description
`objective`	Yes	Plain-language explanation of what the agent is trying to locate.
`pathHints`	No	Optional folders, packages, or relative path globs that should scope the suggested search.
`workspaceRoot`	No	Absolute workspace root to plan against. Defaults to the server workspace.
`knownExactString`	No	Optional exact string to search for when it is already known.
`suspectedPattern`	No	Optional first-pass regex or identifier candidate to plan around.

Output Schema

ParametersJSON Schema

Name	Required	Description
`reasoning`	Yes
`fallbackPlan`	Yes
`mustEnsureIndex`	Yes
`suggestedRegexArgs`	No
`recommendedSequence`	Yes
`recommendedFirstTool`	Yes
`suggestedExplainArgs`	No
`suggestedLiteralArgs`	No

TDQS

A4.2/5.0

Behavior4/5

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

Annotations (readOnlyHint: true) are consistent with the description, which indicates no destructive actions. The description adds behavioral context: the tool plans and recommends, rather than performing a search directly, which is valuable beyond 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 a single, front-loaded sentence with no filler. Every word contributes to the purpose and usage guidance, making it highly concise.

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

Completeness4/5

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

Given the complexity (5 parameters, 1 required, output schema available), the description adequately covers the tool's role as a planner that recommends among sibling tools. It does not detail output or planning logic, but the output schema likely covers that. Minimal but sufficient.

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 description coverage is 100%, so the baseline is 3. The description does not add additional meaning to the parameters; it relies on the schema's descriptions, which are already clear. No extra semantics are provided.

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 clearly states the tool's purpose: 'Plan the MCP-first search workflow for an exploratory objective and recommend...' It specifies the verb (plan), resource (search workflow), and explicitly distinguishes from sibling tools like search.literal, search.regex, index.ensure, and query.explain.

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?

The description indicates when to use the tool: 'for an exploratory objective' and that it will recommend among alternative tools (e.g., ensure index, literal search). It provides clear context but does not explicitly state when not to use it, though the guidance is still effective.

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

search.regexSearch RegexA

Read-only

Find ECMAScript regular-expression matches in indexed workspace files using sparse n-gram pruning before deterministic verification.

ParametersJSON Schema

Name	Required	Description
`flags`	No	ECMAScript regex flags such as `gm` or `u`. Ignore-case searches fall back to a full scan.
`pattern`	Yes	ECMAScript regular expression source without surrounding slashes.
`pathGlobs`	No	Optional relative glob patterns that narrow the search to specific folders or files.
`afterLines`	No	Number of context lines to include after each match. Defaults to 1.
`maxResults`	No	Maximum number of matches to return. Defaults to 100.
`beforeLines`	No	Number of context lines to include before each match. Defaults to 1.
`includePlan`	No	Include the query plan explanation in the structured result.
`workspaceRoot`	No	Absolute workspace root to search. Defaults to the server workspace.
`autoEnsureIndex`	No	Refresh the local index automatically before searching. Defaults to true.

Output Schema

ParametersJSON Schema

Name	Required	Description
`plan`	No
`matches`	Yes
`elapsedMs`	Yes
`queryKind`	Yes
`truncated`	Yes
`matchCount`	Yes
`plannerMode`	No
`fallbackReason`	No
`scannedDocCount`	Yes
`candidateDocCount`	Yes
`coveringGramCount`	No
`extractableAnchors`	No

TDQS

A4/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false. The description adds algorithmic detail ('sparse n-gram pruning before deterministic verification'), which provides performance insights. No contradictions. Slightly above average due to additional context beyond 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 a single sentence of 14 words, highly concise and front-loaded with the main action. No waste.

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

Completeness4/5

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

Given the complexity (9 parameters, output schema exists), the description is brief but adequate. The output schema covers return values. The description misses mentioning fallback behaviors (e.g., ignore-case fallback). Slightly above average due to algorithmic transparency.

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 description coverage is 100%, so parameters are well-documented in the schema. The description does not add additional meaning or interactions beyond the schema. Baseline 3 is appropriate.

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 clearly states 'Find ECMAScript regular-expression matches in indexed workspace files,' specifying a specific verb and resource. It distinguishes from sibling tools like search.literal (literal substring search) and search.plan (planning).

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

Usage Guidelines3/5

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

The description implies usage when a regex pattern is needed, but it does not explicitly provide when-to-use or when-not-to-use guidance, nor does it mention alternatives like search.literal or search.plan. Usage is implied but not contextualized.

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

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

8 tool updatesv0.2.0Jul 26, 2026
- First observeddocument.inspect_terms
- First observedindex.clear
- First observedindex.ensure
- First observedindex.status
- First observedquery.explain
- First observedsearch.literal
- First observedsearch.plan
- First observedsearch.regex

Install Server

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A4.3/5.0

Disambiguation5/5

Each tool has a clearly distinct purpose: index management (ensure, status, clear), search (literal, regex, plan), query explanation (explain), and document inspection (inspect_terms). No functional overlap.

Naming Consistency5/5

All tools follow a consistent 'category.action' dot notation (e.g., index.ensure, search.literal), making naming predictable and easy to understand.

Tool Count5/5

8 tools is well within the ideal 3-15 range. The count is sufficient to cover the domain without being excessive.

Completeness4/5

The tool set covers index lifecycle, two search modes, planning, explanation, and n-gram inspection. A potential gap is the lack of a tool to list indexed files explicitly, but index.status provides similar info. Otherwise, it's well-rounded.

Maintenance

ActivitySlowing

ResponsivenessSyncing

Resources

GitHub Repository

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Maguyva
ai.maguyva
Code intelligence for coding agents: semantic, AST, graph, and full-text search. 279+ languages.
Code Analysis Coding Agents
23
gentlyOAuth
is.gently
Ask a codebase what calls what: search, blast radius, paths between symbols, and diffs.
Code Analysis Developer Tools
1
OrchaOAuth
io.github.westonhancock
Securely search and manage workspace context files for AI agents and teams.
Search File Systems Knowledge & Memory
1
GitHits AOAuth
com.githits
Search public open-source code, documentation, metadata, vulnerabilities, changelogs, and examples.
Developer Tools Documentation Access Search
298

Related MCP Servers

MCP Desktop Tools
Search File Systems Developer Tools
andrey-zhuravl
A
license
Not graded
quality
D
maintenance
Enables searching text across configured local workspaces using ripgrep. Provides secure text search capabilities within defined workspace boundaries through both MCP server and CLI interfaces.
Updated 7 months ago (2026-01-31 10:34 UTC)
MIT
File Search MCP
Developer Tools File Systems Code Analysis
elad12390
A
license
A
quality
D
maintenance
Enables blazingly fast file and content searching in large codebases using ripgrep, with intelligent filtering, fuzzy finding, and directory tree visualization while respecting .gitignore and avoiding common bloat directories.
Updated 3 months ago (2026-05-26 12:56 UTC)
4
25
2
MIT
Cometix Indexerofficial
RAG Systems Search Developer Tools
CometixAI
F
license
Not graded
quality
D
maintenance
A local indexing and retrieval service that enables semantic code search by wrapping Cursor's backend RepositoryService. It provides tools for indexing local workspaces and performing incremental semantic searches with automatic synchronization.
Updated 10 months ago (2025-10-30 13:27 UTC)
68
-
sifs
Code Analysis Search
tristanmanchester
A
license
A
quality
C
maintenance
Extremely fast local hybrid code search for agents.
Updated 3 months ago (2026-05-28 17:40 UTC)
15
2
MIT

Appeared in Searches

Precise search

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/blas0/rev-eng-cursor-regex-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server

rev-eng-cursor-regex-mcp

Features

Requirements

Quick Start From Source

Run Modes

Environment

Verify A Fresh Clone

Claude Desktop Example

Notes

Available Tools

Output Schema

Output Schema

Output Schema

Output Schema

Output Schema

Output Schema

Output Schema

Output Schema

Tool Schema Changelog

Maintenance

Resources

Looking for Admin?

Related MCP Connectors

Related MCP Servers

Cometix Indexerofficial

Appeared in Searches

Latest Blog Posts

MCP directory API