Skip to main content
Glama

MemoRepo

CI GitHub release License: MIT XERJ Corpus Hub contributor memorepo MCP server – quality and maintenance score on Glama

MemoRepo banner

Local-first, read-only code intelligence for coding agents.

MemoRepo turns related GitHub repositories into reproducible context for coding agents. It groups repositories into isolated spaces, captures exact commits as immutable snapshots, indexes their shared code graph with codebase-memory-mcp, and exposes verified source through a read-only Model Context Protocol (MCP) server. It is designed for one developer on one workstation who needs cross-repository context without giving agents arbitrary filesystem or write access.

MemoRepo dashboard showing repository spaces and indexing status

Why MemoRepo

  • Cross-repository context: query several related repositories through one space and one shared code graph.

  • Reproducible evidence: every connection and chat is pinned to an immutable snapshot of exact commits.

  • Source-backed answers: graph search is complemented by direct, exhaustive search over the captured source tree.

  • Narrow access: agents receive space-scoped, read-only tools instead of general filesystem access.

  • Local control: clones, indexes, operational state, and credentials remain in your local environment.

Related MCP server: Ariadne

Quick start

Requirements

  • Docker Desktop on Windows or macOS, or Docker Engine/Desktop on Linux.

  • A GitHub account with access to the repositories you want to index.

Clone the project and start MemoRepo:

git clone https://github.com/abelmaro/MemoRepo.git
cd MemoRepo
docker compose up --build

On first start, the API generates a local control token and prints an unlock link:

Unlock the MemoRepo dashboard: http://127.0.0.1:5173/#token=...

Open that link, then:

  1. Create a space.

  2. Sign in with GitHub when prompted, or configure GH_TOKEN in .env.

  3. Add one or more repositories and wait for the immutable snapshot to become active.

  4. Create a read-only connection and copy the generated MCP configuration into your coding agent.

The link is printed only when the token is created. To unlock another tab later, paste the token shown by docker compose exec api cat /var/lib/memorepo-secrets/control-token. A .env file is optional; copy .env.example only to override defaults. For storage options, agent connection modes, and troubleshooting, follow the complete quickstart.

How it works

  1. A space groups repositories that belong to the same coding context.

  2. MemoRepo checks out selected commits and materializes their source in an immutable, content-addressed store.

  3. The snapshot index combines cross-repository graph discovery with direct source verification.

  4. A space-scoped MCP gateway exposes only bounded, read-only query tools.

  5. Optional in-dashboard chats use the same snapshot and require explicit consent before sending relevant context to the selected inference provider.

MemoRepo never edits, commits, or pushes to managed repositories. It is not designed as a public, network-exposed, or multi-user service.

Security model

  • The API and dashboard bind to 127.0.0.1 by default.

  • The control plane and each MCP connection use separate bearer credentials.

  • Repository credentials are not included in generated MCP configurations or model prompt payloads.

  • Snapshot tools reject arbitrary filesystem paths and sanitize internal paths from responses.

  • The dashboard explains which chat data is sent to a provider before you can consent.

Treat control tokens and generated MCP configurations as secrets. Do not expose MemoRepo through a reverse proxy or bind its ports to a public interface. See the operating contract for the complete trust and data model.

Documentation

Guide

Covers

Quickstart

Installation, GitHub connection, spaces, agents, and troubleshooting

MCP tools

Connection modes, tool contracts, limits, and recommended agent workflow

Operating contract

Runtime support, configuration, data ownership, boundaries, and security

Changelog

Releases and notable changes

Contributing

Contributions are welcome. Read the contribution guide for development setup and validation commands, and follow the Code of Conduct.

Use GitHub Issues for bugs and feature requests. Report vulnerabilities privately according to the security policy.

License

MemoRepo is available under the MIT License.

Available Tools

14 tools
get_architectureC

Return the native CBM architecture summary for this space snapshot, or one project when project is provided.

Inputs: path, detail, aspects, project.

get_code_snippetC

Run native CBM snippet lookup by qualified symbol name.

Inputs: qualified_name (required), project, include_neighbors.

get_graph_schemaC

Return native CBM graph schema details for this space snapshot.

Inputs: project.

index_statusB

Check CBM indexing status for this space snapshot or one project inside it.

Inputs: project.

list_projectsA

List CBM projects available inside this MemoRepo space snapshot.

Inputs: no named parameters.

list_snapshot_filesA

List regular files captured in one repository's immutable snapshot tree. Use this for file inventories and extension/path existence questions; results contain relative paths only and support prefix/glob filtering plus offset pagination.

Inputs: project (required), glob, limit, offset, +1 more.

list_space_repositoriesA

List compact repositories and project names for this MemoRepo space. Branches and detailed metadata are omitted unless explicitly requested.

Inputs: include_details, include_branches.

query_graphA

Run the supported read-only Cypher subset against this space snapshot. max_rows must be between 1 and 25 and is a global limit for projectless calls. Use offset for scoped pagination.

Inputs: query (required), offset, project, max_rows.

read_snapshot_fileA

Read bounded numbered UTF-8 lines from a regular file in one immutable repository snapshot, with digest and truncation metadata.

Inputs: path (required), project (required), end_line, max_bytes, +1 more.

search_codeC

Run native CBM indexed code text search within this space snapshot. Use offset and has_more for pagination; requested limits above 25 use an effective limit of 25. Scoped searches expose the engine's first 250 matches; cross-project searches can page across the combined accessible matches.

Inputs: pattern (required), mode, limit, regex, +6 more.

search_graphC

Run native CBM structured graph search within this space snapshot.

Inputs: label, limit, query, detail, +10 more.

search_snapshot_textB

Search literal text across immutable snapshot files, including files CBM does not index. Paginate to has_more=false and require complete=true before absence conclusions.

Inputs: query (required), glob, limit, offset, +4 more.

snapshot_index_coverageC

Report verified source-integrity coverage for the immutable snapshot by project and file extension, including reported skips, exclusions, quality, and whether the inventory is exhaustive. Candidate files are not claimed as proven CBM graph membership.

Inputs: project.

trace_pathC

Trace a uniquely resolved function or method. Includes USAGE references for callbacks and functions passed as values.

Inputs: function_name (required), mode, depth, detail, +7 more.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3.1/5.0

    Scored across 14 tools

    Disambiguation4/5

    Most tools have clearly separated roles: snapshot filesystem access (list_snapshot_files, read_snapshot_file, search_snapshot_text) versus CBM code-graph access (search_graph, trace_path, get_code_snippet, query_graph). The fuzziest boundaries are search_snapshot_text vs search_code (literal text across all files vs indexed code text) and list_space_repositories vs list_projects, but the descriptions explicitly draw these distinctions. An agent can pick correctly with careful reading, though the two search tools could still be misselected.

    Naming Consistency4/5

    Nearly all tools follow a verb_noun convention (list_snapshot_files, read_snapshot_file, search_snapshot_text, get_architecture, trace_path, search_code), with snapshot tools consistently prefixed by 'snapshot'/'space'. The exceptions are snapshot_index_coverage and index_status, which are noun phrases rather than verb-led, plus a mild inconsistency between 'get_' and 'search_'/'query_' retrieval verbs.

    Tool Count5/5

    Fourteen tools is well within a reasonable range and splits cleanly into two coherent surface layers (five snapshot-integrity tools, nine code-graph tools). Each tool corresponds to a distinct operation with no filler or duplicated capability, so the count is well matched to the server's dual purpose.

    Completeness4/5

    The read-only surface covers inventory, coverage reporting, file reading, literal search, project listing, indexing status, architecture, schema, graph search, path tracing, snippet lookup, and a Cypher escape hatch — a solid lifecycle for inspecting a code snapshot. Minor gaps remain: there is no way to enumerate snapshots/versions or diff two snapshots, and symbol-reference discovery depends on trace_path rather than a dedicated callers/callees tool.

    Maintenance

    ActivityMaintained
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      C
      maintenance
      Provides code intelligence for AI coding agents by indexing repositories into a hybrid knowledge graph, enabling agents to query dependencies, impact, and context through 28 MCP tools.
      4
      Apache 2.0
    • A
      license
      Not graded
      quality
      D
      maintenance
      Semantic code index and gatekeeper that exposes 14 read-only MCP tools for AI agents, enabling symbol search, definition lookup, reference finding, and impact analysis via static analysis of codebases.
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables coding agents to query a local, multi-repo code graph for symbol exploration, blast radius analysis, co-change mining, and durable code-anchored memory via MCP tools.
      271 npm
      16
      Business Source 1.1