Skip to main content
Glama
donliggett

mcp-context-window

by donliggett
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

Related Servers

Alternatives to mcp-context-window

No user-submitted related servers found.

    Related Servers

    • membot

      evantahler
      A
      license
      Not graded
      quality
      A
      maintenance
      Provides a persistent, versioned, and searchable context store for AI agents with local embedding and hybrid search.
      19 npm
      3
      MIT

    • repo-map MCP server

      allengox1994-creator
      A
      license
      Not graded
      quality
      B
      maintenance
      Provides a unified context layer for Cursor's agent with lossless token savings and verifiable memory, enabling efficient code exploration and cross-session continuity.
      10 npm
      1
      MIT

    • ai-memory-mcp

      zhanpu89
      A
      license
      A
      quality
      D
      maintenance
      Provides persistent session memory for AI assistants, enabling them to store, search, and retrieve conversation summaries across sessions via the Model Context Protocol.
      10
      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

    A4.3/5.0

    Scored across 15 tools

    Disambiguation5/5

    The tools are cleanly divided into context/session memory tools and document ingestion tools, with each serving a distinct operation: append, recall, compact, status, update, ingest, outline, window, search, summarize, list, and forget. Even the two retrieval-style tools, context_recall and doc_search, are clearly scoped to different stores by their descriptions.

    Naming Consistency4/5

    All names are lowercase snake_case and consistently grouped with context_ and doc_ prefixes, mostly following a verb-action pattern. Minor deviations exist: context_status and doc_window use nouns as commands, but the overall convention is readable and predictable.

    Tool Count5/5

    At 15 tools, the server is at the upper edge of a well-scoped set, but every tool maps to a distinct and useful operation across two related subdomains. There are no redundant utilities, and the count feels justified for the stated context-window and document-management purpose.

    Completeness4/5

    The server covers the core session lifecycle (open/resume, append, recall, compact, status, update, list) and the document lifecycle (ingest, outline, read, search, summarize, list, forget). The main gap is the absence of an explicit session deletion or close tool, though agents can still work around this by leaving sessions unused.

    Maintenance

    ActivityMaintained
    ResponsivenessNo issues

    Resources