Skip to main content
Glama

Related Servers

Alternatives to Metis

No user-submitted related servers found.

    Related Servers

    • F
      license
      A
      quality
      D
      maintenance
      Enables Claude to search a local hybrid retrieval index of research papers and ingest new PDFs, providing research-paper memory queryable directly through natural language.
      2
      -
    • A
      license
      A
      quality
      B
      maintenance
      Enables Claude to search arXiv and Semantic Scholar, read paper metadata and abstracts, trace citing papers, and export compile-safe BibTeX, all inside the chat. It also keeps a persistent reading list with tags and notes across conversations.
      7
      MIT
    • F
      license
      Not graded
      quality
      D
      maintenance
      Enables semantic search and conversational querying across a personal research library of PDFs, DOCX, and other documents using a vector database. It provides tools for document summarization, finding related papers, and high-accuracy retrieval for AI clients like Claude Desktop.
      -
    • A
      license
      A
      quality
      D
      maintenance
      Give Claude the ability to read, search, and synthesize across your entire PDF library. Built on PaperQA2.
      2
      2
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables Claude Code and Claude Desktop to run multi-agent literature research: searching arXiv and OpenAlex for papers and producing cited literature reviews. Every cited statement is fact-checked against the paper it cites, so references cannot be fabricated.
      MIT
    • A
      license
      B
      quality
      B
      maintenance
      Gives agents a persistent local knowledge graph of companies, sourced claims and investment theses, so new research builds on what was already concluded and every fact keeps its citation. It also watches SEC filings and news, raises alerts on the theses they affect, and supports onboarding, challenge, memo and review workflows.
      4
      45
      22 PyPI
      1
      Apache 2.0

    TDQS

    B3/5.0

    Scored across 291 tools

    Disambiguation2/5

    Many tools have overlapping purposes: recall, search_memory, semantic_search, get_context, and surface_relevant_context all retrieve prior knowledge; search_library, search_literature, search_literature_extended, search_fulltext, search_pdf_knowledge, and ask_library all search literature/PDFs; scan_news, scan_library, scan_literature, scan_pubmed_alerts, scan_openalex, and full_scan overlap on discovery. Descriptions often clarify boundaries, but with 291 tools the agent still faces several near-duplicate choices.

    Naming Consistency3/5

    Most names use snake_case, but the convention is mixed: some are verb_noun (get_project_status, create_task), others are noun phrases or terse labels (data_memory, institution_actions, kg_paths, viz_library_overview, recall). Abbreviations such as kg_, viz_, and dhis2_ add inconsistency, though names remain generally readable.

    Tool Count1/5

    291 tools is an extreme mismatch for a single MCP server, far beyond the 3-15 well-scoped range and well past the 25+ threshold. The surface spans memory, literature, projects, visualization, backup, DHIS2, courses, templates, and more, making the active tool set unwieldy and difficult for an agent to navigate.

    Completeness3/5

    The server covers many lifecycles broadly (tasks and projects have create/read/update/delete, memory has multiple layers, literature ingestion and search are extensive), so it is not severely incomplete. However, some areas are partial or asymmetric, such as ideas with capture/get but no update/delete, and many adjacent operations are split across hidden or overlapping tools rather than forming clean complete surfaces.

    Maintenance

    ActivityMaintained
    ResponsivenessOutdated data