Skip to main content
Glama
giseungNoh

Learning MCP

by giseungNoh
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Related Servers

Alternatives to Learning MCP

No user-submitted related servers found.

    Related Servers

    • DevLog

      ericd21
      A
      license
      Not graded
      quality
      B
      maintenance
      Enables developers to maintain a local engineering journal, log work manually or from git history, and let AI assistants query, summarize, and draft standup updates, changelogs, and retro notes.
      MIT

    • obsidian-dev-memory

      jmjava
      A
      license
      A
      quality
      B
      maintenance
      Provides AI coding assistants persistent engineering memory stored as Markdown files in an Obsidian vault, enabling project context retrieval, session capture, decision recording, and memory search without requiring Obsidian to be running.
      7
      MIT

    • Recall

      jerrl10
      A
      license
      A
      quality
      B
      maintenance
      Turns AI coding conversations into structured Markdown notes in an Obsidian vault, and retrieves that knowledge in later sessions so assistants can reuse prior conclusions.
      5
      2
      MIT

    • vault-mcp

      andreymudri
      A
      license
      A
      quality
      B
      maintenance
      Enables coding agents to use an Obsidian vault as long-term memory, with search, reading, and writing of notes, plus automatic capture of learnings that are propagated to MOCs, daily notes, and the knowledge index with git commits.
      9
      32 npm
      MIT
    Deploy Server
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    TDQS

    B3.3/5.0

    Scored across 10 tools

    Disambiguation5/5

    Each tool targets a distinct phase of the learning workflow: feature lifecycle, context, decision records, debug attempts, session sync, manifest retrieval, evidence details, and final review. There is no meaningful overlap that would cause an agent to pick the wrong tool.

    Naming Consistency5/5

    All tool names follow a clear snake_case verb_noun pattern, with get_, record_, start_, save_, finish_, and sync_ as predictable action prefixes. The naming is internally consistent and easy to navigate.

    Tool Count5/5

    Ten tools is well-scoped for a learning-tracking MCP server covering feature lifecycle, context, decision/debug capture, Codex session synchronization, evidence retrieval, and review export. Each tool has a clear purpose and none feel redundant.

    Completeness4/5

    The core lifecycle is well covered: start a feature, capture decisions and debugging, sync sessions, retrieve evidence, save reviews, and finish. The main gap is the lack of update/correction or delete/abandon operations for recorded data, though this can be worked around by appending new records.

    Maintenance

    ActivityMaintained
    ResponsivenessNo issues

    Resources