Skip to main content
Glama
NLY22

periscope-mcp

by NLY22
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Related Servers

Alternatives to periscope-mcp

No user-submitted related servers found.

    Related Servers

    • Infobroker

      flukeatzerocool
      A
      license
      A
      quality
      A
      maintenance
      An MCP-native research assistant — search backend, intent-routing, and writing pipeline that carries a question through search, verification, and writing, delivering whatever research you need: quick answers, verified sources, or a finished document.
      4
      7
      388 npm
      MIT
    • genpark-deep-research-consensus-engine-skill by Alpha-Park

      genpark-deep-researchofficial

      Alpha-Park
      F
      license
      Not graded
      quality
      B
      maintenance
      Enables AI agents to perform deep research across multiple sources, arbitrating consensus while evaluating source authority and detecting contradictions. It integrates via MCP with clients like Claude Desktop and Cursor to deliver deterministic, structured research dossiers.
      7
      -

    • Vajra

      mishraxram
      A
      license
      Not graded
      quality
      A
      maintenance
      A local stdio MCP server that exposes tools for running evidence-first research with source-linked, replayable reports, plus replay, citation-audit, and Agent Reach health checks. It preserves fetched page text, exact quote offsets, hashes, and run traces so a client can verify that quotes match retrieved sources, while withholding arbitrary shell or local-file access.
      1
      MIT

    • wigolo

      KnockOutEZ
      A
      license
      A
      quality
      A
      maintenance
      Provides local-first web intelligence over MCP with tools for search, fetch, crawl, extract, cache, find-similar, research, and autonomous agent loops, requiring no API keys.
      10
      1,063 npm
      5,446
      AGPL 3.0
    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

    C2.8/5.0

    Scored across 27 tools

    Disambiguation4/5

    Most tools target a clear resource+action: individual pipeline stages (fetch/score/filter/enrich), distinct run reads (meta/stage/summary), and distinct research lifecycle steps. Minor overlaps exist between ps_generate_summary vs ps_get_run_summary, ps_corpus_stats vs ps_get_metrics, and ps_corpus_search vs ps_corpus_recent, but descriptions differentiate them adequately.

    Naming Consistency4/5

    All tools share a consistent ps_ snake_case prefix, which makes the set highly scannable. The only deviation is that some names are verb-first (ps_get_claim, ps_list_runs, ps_validate_config) while others are domain-first (ps_corpus_search, ps_research_start), but the pattern remains predictable within each domain.

    Tool Count3/5

    At 27 tools this is heavier than typical, though the server genuinely spans several domains (corpus, claims, pipeline stages, research sessions, webhook). The eight individual pipeline-stage tools plus ps_run_pipeline create some redundancy, so the surface could be trimmed.

    Completeness4/5

    Coverage is broad and lifecycled: corpus ingest/search/stats, claim inspection, full pipeline plus per-stage control, research start/followup/step/draft/edit/answer/status/list, and webhook notify. Only minor gaps exist (e.g., no explicit corpus/claim deletion or run cancellation), which agents can work around.

    Maintenance

    ActivityMaintained
    ResponsivenessNo issues

    Resources