shakespeare-monologues-mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@shakespeare-monologues-mcp find monologues from Hamlet by male characters"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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 |
| Free-text search (character / play / first line) + filters: |
| One monologue's index entry by numeric |
| A random monologue, optional |
| Every play with its classification and monologue count. |
| Every monologue spoken by a named character. |
| The current Monologue of the Day (latest social post). |
| A monologue's full text + its modern-English paraphrase (AI-generated; may be null if not yet generated). |
| AI-generated summary of the scene a monologue is in (by monologue id). |
| AI-generated summary of a play (by title). |
| 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
nullwhere 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-mcpOver 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/mcpOr 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.txtdirectly.
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.
Available Tools
9 toolsget_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
Scored across 9 tools
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.
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.
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.
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
Related MCP Connectors
Provides metadata information to AI agents through the search API.
Search 16,000+ API operations and 95 built tools by need, then call any of them by name
Web knowledge fetching tools for your agent.
Agent-first tool search. Start with search_tools({job: "your task in plain words"}); free, no key.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables searching scholarly literature via the OpenAlex database, with tools for full-text search, work details, citation lookup, and author queries.MIT
- AlicenseNot gradedqualityCmaintenanceProvides 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 npmMIT
- AlicenseBqualityDmaintenanceEnables exploring and retrieving classic poems from PoetryDB via 12 MCP tools for catalog, search, and discovery, including by author, title, lines, and poetic forms.1250 npm2MIT
- AlicenseNot gradedqualityCmaintenanceEnables 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 npmMIT