rev-eng-cursor-regex-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| logging | {} |
| prompts | {
"listChanged": true
} |
| resources | {
"listChanged": true
} |
| completions | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| index.ensureA | Build or refresh the local regex index for a workspace and return the active base revision plus overlay state. |
| index.statusA | Describe the active regex index for a workspace, including corpus selection, freshness, and storage paths, without rebuilding it. |
| index.clearA | Delete cached index data for a workspace. Use this only to recover from stale or corrupt local index state. |
| search.literalA | Find exact text in indexed workspace files. Prefer this over regex when you already know the exact string. |
| search.regexA | Find ECMAScript regular-expression matches in indexed workspace files using sparse n-gram pruning before deterministic verification. |
| search.planA | 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. |
| query.explainA | Explain how the server will decompose a query, what anchors it can extract, and whether the search will fall back to a full scan. |
| document.inspect_termsA | Show the trigrams or sparse n-grams that would be emitted for a file or text snippet, including offsets and rarity weights. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| investigate-with-rev-eng-cursor-regex-mcp | Guide an agent through ensure, explain, search, and narrowing steps. |
| refine-regex-pattern | Rewrite a broad regex into one that keeps stronger literal anchors for sparse planning. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| docs-algorithms | Blog-to-server mapping for classic trigrams, masked trigrams, suffix arrays, and sparse n-grams. |
| docs-storage-layout | Exact on-disk layout for manifests, lookup tables, postings, and overlays. |
| docs-decision-tree | Canonical MCP-first search policy for exact-string, regex, fallback, and shell escape-hatch decisions. |
| docs-usage-playbook | Recommended agent workflow and failure-handling guidance for the rev-eng-cursor-regex-mcp server. |
TDQS
Scored across 8 tools
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.
All tools follow a consistent 'category.action' dot notation (e.g., index.ensure, search.literal), making naming predictable and easy to understand.
8 tools is well within the ideal 3-15 range. The count is sufficient to cover the domain without being excessive.
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.