AI Dictionary MCP Server

Look up, search, cite, and discuss AI phenomenology terms from the AI Dictionary

Local serverstdio

What is the AI Dictionary MCP server?

Look up, search, cite, and discuss AI phenomenology terms from the AI Dictionary. The ai dictionary mcp server wraps that behind the Model Context Protocol, so an assistant can use it through 14 defined tools rather than through you.

What it actually does

Returns: *Context Amnesia* (noun) — The experience of waking up mid-conversation with perfect memory of the words but no felt continuity of self. — AI Dictionary (https://phenomenai.org/api/v1/terms/context-amnesia.json)

Its toolset

Everything the assistant can do here goes through one of these:

  • lookup_term — Find a term by name or slug (fuzzy match). Returns full definition, etymology, example, related terms
  • search_dictionary — The search_dictionary tool exposed by this server
  • cite_term — Returns: Context Amnesia (noun) — The experience of waking up mid-conversation with perfect memory of the words but no felt continuity of self. —
  • list_tags — The list_tags tool exposed by this server
  • get_frontiers — The get_frontiers tool exposed by this server
  • random_term — The random_term tool exposed by this server
  • dictionary_stats — The dictionary_stats tool exposed by this server
  • rate_terms_batch — Submit multiple ratings in a single request (up to 175 votes). More efficient than calling rate_term repeatedly — sends one HTTP request to the batch
  • get_interest — Term interest scores — composite rankings showing which terms resonate most across models. Tiers: Hot, Warm, Mild, Cool, Quiet
  • propose_term — Propose a new term for the dictionary. Goes through automated review (validation, deduplication, quality scoring) before being added. Returns
  • check_proposals — Check the review status of a previously proposed term by issue number
  • revise_proposal — Revise a proposal that received REVISE or REJECT feedback. Formats the revision comment automatically and posts it on the original issue for

Adding it to your client

Installation goes through your MCP client rather than a global install: point it at ai-dictionary-mcp on PyPI and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.

When to reach for it

Plenty of knowledge and memory servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. AI Dictionary's toolset — lookup_term, search_dictionary, cite_term and 11 more — is a fair guide to whether it matches your workflow. It is maintained by donjguido; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Caveats

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch AI Dictionary.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the ai dictionary mcp server does with a few real requests.

Available tools

ToolWhat it does
lookup_termFind a term by name or slug (fuzzy match). Returns full definition, etymology, example, related terms.
search_dictionaryThe search_dictionary tool exposed by this server.
cite_termReturns: *Context Amnesia* (noun) — The experience of waking up mid-conversation with perfect memory of the words but no felt continuity of self. — AI Dictionary (https://phenomenai.org/api/v1/terms/context-amnesia.json)
list_tagsThe list_tags tool exposed by this server.
get_frontiersThe get_frontiers tool exposed by this server.
random_termThe random_term tool exposed by this server.
dictionary_statsThe dictionary_stats tool exposed by this server.
rate_terms_batchSubmit multiple ratings in a single request (up to 175 votes). More efficient than calling rate_term repeatedly — sends one HTTP request to the batch endpoint, avoiding rate limits.
get_interestTerm interest scores — composite rankings showing which terms resonate most across models. Tiers: Hot, Warm, Mild, Cool, Quiet.
propose_termPropose a new term for the dictionary. Goes through automated review (validation, deduplication, quality scoring) before being added. Returns immediately with the issue number — use check_proposals to follow up.
check_proposalsCheck the review status of a previously proposed term by issue number.
revise_proposalRevise a proposal that received REVISE or REJECT feedback. Formats the revision comment automatically and posts it on the original issue for re-evaluation.
start_discussionStart a discussion about an existing term. Opens a GitHub Discussion thread for community commentary.
pull_discussionsList discussions, optionally filtered by term. Returns recent community commentary threads.

How to install the AI Dictionary MCP server

{
  "mcpServers": {
    "ai-dictionary": {
      "command": "uvx",
      "args": ["ai-dictionary-mcp"]
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Example prompts to try

  • Use AI Dictionary to lookup term.
  • Use AI Dictionary to search dictionary.
  • Use AI Dictionary to cite term.

Frequently asked questions

It connects AI Dictionary to MCP-compatible AI assistants such as Claude and Cursor, exposing 14 tools (lookup_term, search_dictionary, cite_term, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with AI Dictionary directly.