Skip to main content
Glama
shakespeare-monologues-mcp

shakespeare-monologues-mcp

Shakespeare's Monologues — MCP server

A small, read-only Model Context Protocol server that lets MCP-capable AI clients search and fetch Shakespeare monologue metadata from shakespeare-monologues.org.

It's a thin, stateless wrapper over the site's public JSON index (/api/monologues.json) — no database, no secrets. Every result carries the monologue's permalink url (where the full text, scene context, and modern-English paraphrase live) and an attribution note.

Tools

Tool

What it does

search_monologues

Free-text search (character / play / first line) + filters: gender, play, style, act, limit.

get_monologue

One monologue's index entry by numeric id.

random_monologue

A random monologue, optional gender / play filters.

list_plays

Every play with its classification and monologue count.

list_all_monologues_for_a_character

Every monologue spoken by a named character.

get_monologue_of_the_day

The current Monologue of the Day (latest social post).

get_paraphrased_monologue

A monologue's full text + its modern-English paraphrase (AI-generated; may be null if not yet generated).

get_scene_summary

AI-generated summary of the scene a monologue is in (by monologue id).

get_play_summary

AI-generated summary of a play (by title).

send_feedback

Lets an agent report a missing capability, a problem, or praise. Added by the PostHog analytics SDK; only present when analytics is on.

The paraphrase and summaries are AI-generated (Claude) and only partially cached so far, so those tools return null where content hasn't been generated yet.

Related MCP server: mcp-bookbrainz

Run locally

Two transports, same tools. server.ts builds the tool surface and knows nothing about how it's reached; index.ts serves it over HTTP and stdio.ts over stdio.

Over stdio, the way an MCP client spawns a local server:

npx shakespeare-monologues-mcp

Over HTTP, which is how the hosted instance runs:

npm install
npm run build
npm start          # listens on :3000, POST /mcp   (set PORT to change)

Health check: GET /health → {"ok":true}.

Neither mode needs credentials — the server reads the site's public JSON index. Set MONOLOGUES_API_URL to point it elsewhere, and POSTHOG_PROJECT_API_KEY="" to disable analytics.

Connecting a client

Remote MCP means users add a URL, no install. In a client that supports remote / custom MCP servers (Claude Desktop connectors, etc.), add:

https://mcp.shakespeare-monologues.org/mcp

Or run it yourself over stdio, with no hosted dependency:

{
  "mcpServers": {
    "shakespeare-monologues": {
      "command": "npx",
      "args": ["-y", "shakespeare-monologues-mcp"]
    }
  }
}

For clients configured with a JSON config file, use the streamable-HTTP transport:

{
  "mcpServers": {
    "shakespeare-monologues": {
      "type": "streamable-http",
      "url": "https://mcp.shakespeare-monologues.org/mcp"
    }
  }
}

For a client that only speaks stdio, bridge to the remote server with mcp-remote:

{
  "mcpServers": {
    "shakespeare-monologues": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://mcp.shakespeare-monologues.org/mcp"]
    }
  }
}

Note on "autonomous" use: there's no mechanism today for an arbitrary agent to discover and use this with zero user action — a client/platform still has to connect it. For truly zero-setup access, agents can hit the plain JSON API (/api/monologues.json) and /llms.txt directly.

License

  • Code: MIT.

  • Data served through it: © shakespeare-monologues.org, CC BY-NC-SA 4.0 — please keep the attribution that each tool response includes.


shakespeare-monologues-mcp MCP server

Available Tools

9 tools
get_monologueAInspect

Fetch one monologue's catalogue entry by its numeric id. Follow the returned url for the full text.

Inputs: id, monologue_id.

get_monologue_of_the_dayAInspect

The current 'Monologue of the Day' — the piece most recently posted to the site's social feeds.

Inputs: no named parameters.

get_paraphrased_monologueAInspect

Fetch a monologue's full text alongside its modern-English, line-by-line paraphrase. The paraphrase is AI-generated (Claude) and may be null if it hasn't been generated yet — the url always has the monologue itself.

Inputs: id, monologue_id.

get_play_summaryAInspect

Fetch an AI-generated summary of a play (e.g. 'Hamlet', 'The Tempest'). May be null if not generated yet.

Inputs: play (required).

get_scene_summaryAInspect

Fetch an AI-generated summary of the scene a monologue appears in (context for the speech). May be null if not generated yet.

Inputs: id, monologue_id.

list_all_monologues_for_a_characterAInspect

List every monologue spoken by a given character (e.g. 'Hamlet', 'Rosalind'). Matches the character name exactly first, then as a substring.

Inputs: character (required), limit.

list_playsAInspect

List Shakespeare's plays with their classification (Comedy/History/Tragedy) and monologue counts.

Inputs: no named parameters.

random_monologueAInspect

Return one random monologue, with optional gender/play filters. Useful for a suggestion when the user is undecided.

Inputs: play, gender.

search_monologuesAInspect

Search Shakespeare monologues by free text (matches character, play, or first line) plus optional filters. Returns matches, each with a permalink url.

Inputs: act, play, limit, query, +2 more.

Tool Schema Changelog

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

Loading tool schema changelog…

    TDQS

    A4/5.0

    Scored across 9 tools

    Disambiguation4/5

    Each tool targets a distinct retrieval or summary function, and the descriptions generally clarify boundaries. The main ambiguity is between search_monologues and list_all_monologues_for_a_character, since both can return monologues for a character, though one is a broad search and the other a focused listing.

    Naming Consistency4/5

    Most tools follow a clear snake_case verb_noun pattern like list_plays, search_monologues, and get_monologue. random_monologue breaks the verb-first convention, and a few names are verbose, but the overall style remains predictable.

    Tool Count5/5

    Nine tools is well-scoped for a Shakespeare monologue server, covering browsing, searching, retrieval, random/daily selection, paraphrases, and summaries. Each tool earns its place without feeling bloated or redundant.

    Completeness4/5

    The surface covers the core workflows of discovering, searching, retrieving, and contextualizing monologues. Minor gaps exist, such as no direct list-monologues-by-play endpoint and get_monologue requiring an external URL for the full text, but agents can work around these.

    Maintenance

    ActivityNo data
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables searching scholarly literature via the OpenAlex database, with tools for full-text search, work details, citation lookup, and author queries.
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Provides access to BookBrainz open book metadata, enabling search, lookup, and browsing of works, editions, authors, publishers, and series via natural language or direct tool calls.
      64 npm
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables AI agents to explore a public-domain poetry collection by searching poems by title, finding poems whose lines contain a given phrase, pulling one or more random poems, and listing available authors. It returns full poem text with author and line-count details, and works either through a hosted gateway or as a local stdio server without an account.
      96 npm
      MIT