MCP.Market

LLMScribe MCP server

by AMRITO-KUNDU·io.github.AMRITO-KUNDU/llmscribe·v1.3.0·13 stars
No reviews yet

Deterministic local project map, search and file reader for AI agents.

A92/100grade A
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
A92/100

not scanned yet

Adoption
Growing

13 stars9 downloads/wk

Reviews

Write one

Nobody has reviewed LLMScribe yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

LLMScribe tools

No tool declarations could be read from the package source. They show once the server is installed.

Not scanned yet. New listings are scanned within a day or two of arriving.

How LLMScribe compares

Against every graded Web search MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
92/100
higher than 90% of 3,470 Web search servers
GitHub stars
13
more than 86% of 1,786 Web search servers
Downloads a week
9
more than 2% of 827 Web search servers with a package

Release history: 2 versions in the registry since 2026-10-13, latest 2026-10-25, typically one every 12 days.

Install LLMScribe in Claude Code, Cursor or VS Code

claude mcp add llmscribe -- uvx llmscribe
Add to Cursor

What the publisher says

From the LLMScribe repository's README, as published. We do not edit it. Read it on GitHub

<!-- mcp-name: io.github.AMRITO-KUNDU/llmscribe --> <img src="https://raw.githubusercontent.com/AMRITO-KUNDU/llmscribe/main/docs/public/favicon.svg" height="200" alt="LLMScribe"

LLMScribe

Turn any code repository into clean, structured, deterministic data. No AI. No embeddings. No hidden ranking. Open source and available as a free hosted MCP.

Pst. Hey, you, join our stargazers :)

Why LLMScribe?

  • Deterministic: Same input, predictable output. No LLM, embeddings, or AI ranking
  • Repository-first: Works with local projects and public GitHub repositories, no cloning required
  • Structured output: Machine-readable JSON for every operation
  • Fast discovery: Map a project, search it, then retrieve exactly what you need
  • Dependency-aware: Understand local, external, and unresolved dependencies
  • Git-aware: Inspect status and unified diffs
  • Agent ready: Connect LLMScribe to any AI agent or MCP client with a single config block
  • Multiple interfaces: CLI, MCP, GUI, and a programmatic core, all sharing the same engine
  • Open source: Apache-2.0, self-hostable, and free forever

LLMScribe doesn't try to be the intelligence. It provides the data that intelligence needs.

Feature Overview

Core Tools

More

Quick Start

Install LLMScribe from PyPI:

pip install llmscribe

Then point it at any project directory, or (through the MCP tools) at a public GitHub repo. No API key needed.

The projectmap(...), search(...), read(...) snippets below show MCP tool calls**. The same operations are available from the CLI (local directories) and from Python through llmscribe.core (see Python API).

Map

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

LLMScribe: common questions

Is LLMScribe MCP server safe?
Yes, by our scan: it is graded A (92/100). Read the LLMScribe safety report
How do I install LLMScribe?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does LLMScribe need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is LLMScribe maintained?
The last commit was 22 days ago (2026-10-13). The latest release is v1.3.0.
What can I use instead of LLMScribe?
Servers from other publishers that do the same job: Repomix MCP server, Google Maps MCP Server and ContextStream MCP Server.
How does LLMScribe compare with other Web search MCP servers?
safety score 92/100 (higher than 90% of 3,470 Web search servers); github stars 13 (more than 86% of 1,786 Web search servers); downloads a week 9 (more than 2% of 827 Web search servers with a package). Full comparison.

Alternatives to LLMScribe

Same job from other publishers: the closest match first, then the best rated.

  • Repomix
    Pack local or remote codebases into AI-friendly files that LLMs and coding agents can read or search
    A
  • Google Maps MCP Server
    18 Google Maps tools for AI agents — geocode, search, directions, weather, and more.
    B
  • ContextStream MCP Server
    The context platform for AI agents: code search, team decisions, and grounded project context.
    A
  • ThoughtDAG
    Search local AI conversations by file or phrase and recall source turns. Four read-only tools.
    A
  • Everything Search
    Fast file search: Everything SDK on Windows, Spotlight (mdfind) on macOS, locate/plocate on Linux.
    A