Skip to main content
Glama

Server Details

Team memory for AI coding agents and code reviews, reviewed by humans and served over MCP.

If you are the author of this connector, you can claim ownership. Claimed connector authors can inspect health checks, view analytics, and manage their listing.
Status
Healthy
Uptime
100.0% over the last 24 hours
OAuth
Works in Glama
Last Tested
Transport
Streamable HTTP · MCP 2025-11-25
URL
ChatGPT
–
Claude
–

TDQS

A3.9/5.0

Scored across 6 tools

Disambiguation4/5

The tools mostly have clear, distinct roles: repo discovery, repo context, memory search, warnings, proposing memories, and session summaries. Some overlap remains between get_relevant_warnings, get_repo_context, and search_memory, and between propose_memories and record_session_summary, but descriptions give useful timing cues.

Naming Consistency5/5

All tool names use snake_case with a verb_noun structure: get_*, list_*, search_*, propose_*, and record_*. The pattern is predictable and readable throughout.

Tool Count5/5

Six tools is well-scoped for a team-memory/repo-context server. Each tool covers a distinct part of the workflow without excessive surface area.

Completeness4/5

The surface covers discovery, context retrieval, memory search, warnings, proposal, and session recording, which supports the main agent workflow. Minor gaps exist around explicit memory update/delete or approval operations, though human review may handle those outside the tool set.

Available Tools

6 tools
get_relevant_warningsGet relevant warningsA
Read-onlyIdempotent
Inspect

Risk/failure memories for the files you're about to edit. Call before editing sensitive files.

Inputs: repo (required), files (required).

get_repo_contextGet repo contextA
Read-onlyIdempotent
Inspect

Stack, package manager, key commands, and known risks for a repo. Call before starting work.

Inputs: repo (required).

list_reposList Memmo reposA
Read-onlyIdempotent
Inspect

List the repos this token can access (id, owner/name, project). Use to find the repo identifier.

Inputs: no named parameters.

propose_memoriesPropose Memmo memoriesAInspect

Record durable, reusable knowledge (conventions, architecture, commands, risks, decisions) as PROPOSED memories for human review. Keep each ATOMIC (one fact) and CONCISE (1–3 sentences). Use supersedes with an id from search_memory to correct an outdated memory.

Inputs: repo (required), memories (required).

record_session_summaryRecord a Memmo session summaryBInspect

Submit what you just did (task, summary, files, commands, errors) so Memmo can propose memories for review.

Inputs: repo (required), task, errors, summary, +2 more.

search_memorySearch Memmo memoryA
Read-onlyIdempotent
Inspect

Search the team's approved memory for a repo (rules, architecture, commands, decisions, risks, past failures). Call it while planning — with a one-line summary of what you intend to do — and before non-trivial changes. Results marked 'replaces' are the current decision.

Inputs: repo (required), query (required), limit.

Tool Schema Changelog

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

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      C
      maintenance
      Shared, code-grounded memory for developers and their coding agents. Capture a learning once and the whole team plus every agent recalls it; memory is grounded in your code and stored as git-tracked JSON reviewed in PRs, with citations validated on write and stale memory withheld from recall. Works with any MCP client.
      11
      41
      GPL 3.0
    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables teams and their AI agents to publish work, review it down to individual blocks, route feedback back to the originating AI, and accrete reviewed work into a shared recallable memory through an MCP connection to Claude, Cursor, Codex, and other clients.
      BSD 2-Clause "Simplified"
    • A
      license
      A
      quality
      B
      maintenance
      MCP server that gives coding agents persistent, verified memory of codebase decisions, conventions, and skills, with evidence-based claims that are re-checked via git hooks and human-gated review. Enables memory search, propose/approve, chat harvesting, and critique across MCP-compatible tools.
      21
      87 npm
      1
      MIT
    • A
      license
      A
      quality
      B
      maintenance
      Enables AI coding agents to share a persistent, git-backed team memory, automatically committing and syncing decisions, solutions, gotchas, statuses, and handoffs across projects and MCP clients.
      30
      1
      MIT
    Try in Browser

    Glama MCP Gateway

    Add one secure layer between your agents and this server.

    Resources