Dictionary Api for AI agents

The Merriam-Webster Dictionary API gives developers programmatic access to definitions, etymologies, pronunciations, and synonyms for English words, used to add reference lookups to apps and writing tools. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.

EducationAPI keyMCP + RESTdictionaryapi.com
AUDIT LOG · DICTIONARY APIPOLICY: acme-support
09:41:07 · claude · u_8f2read
dictionary_api.get_word_definition_v2
Get Word Definition✓ allowed · 212ms
EVERY DICTIONARY API CALL, ON THE RECORD
01 · USE CASES

What agents do in Dictionary Api.

01

Define a term for a draft

Look up a word's definition and part of speech while an agent edits a document for clarity.

02

Check spelling and usage

Pull a word's entry to confirm correct usage before it goes into customer-facing copy.

03

Read-only reference lookups

Keep every lookup read-only, since the dictionary itself has nothing to write back to.

02 · ACTIONS

1 Dictionary Api actions, graded by risk.

Every Dictionary Api action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.

read

1

Look things up. Allowed by default.

  • dictionary_api.get_word_definition_v2
    Get Word Definition

write

0

Create and change things. Allow, or ask the user first.

  • No write actions.

destructive

0

Delete, cancel or archive. Ask first, or deny outright.

  • No destructive actions.
03 · HOW IT WORKS

Dictionary Api in three steps.

  1. 01Your users connect Dictionary ApiThey add their Dictionary Api api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, and writes like “updates” can wait for the user to approve.
  3. 03Any agent can actYour agent calls Dictionary Api through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
POLICY.TS
await arc0.policies.set('dictionary_api', {
  read: 'allow',
  write: 'ask',        
  destructive: 'deny',  
})

# Claude Code: the same connection, one URL
$ claude mcp add --transport http arc0 \
    https://mcp.arc0.ai/u/u_8f2
04 · AUTH AND DATA

How Dictionary Api connects.

Users add their Dictionary Api api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

The same Dictionary Api connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →

AUTH
API key
CREDENTIALS
Per-tenant encrypted vault
MODEL SEES
Results only, never credentials
AUDIT LOG
Every call, on every plan
05 · WORKS WITH

Use Dictionary Api from any agent.

Claude
ChatGPT
Cursor
Codex
VS Code
OpenAI Agents SDK
Claude Agent SDK
Vercel AI SDK
Mastra
LangGraph
07 · FAQ

Dictionary Api and Arc0, answered.

Q01

Can I use Dictionary Api with Claude, ChatGPT or Cursor?

Yes. Connect Dictionary Api to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the Dictionary Api actions you allow.

Q02

How do users connect Dictionary Api?

Users add their Dictionary Api api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

Q03

Which Dictionary Api actions can my agent take?

1 in total: 1 read, 0 write and 0 destructive. Your policies decide which of them each agent may call.

Q04

Can I make my agent read-only in Dictionary Api?

Yes. Allow read actions and deny writes in the Dictionary Api policy. Your agent can still look things up, and any write it attempts is blocked and logged.

Q05

Can my own backend call Dictionary Api too?

Yes. The same Dictionary Api connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.

Get started

Plug Dictionary Api into your agent.

Your users connect Dictionary Api once, under your brand. Your agent gets 1 actions behind your policies, with every call on the record.

Free to build · MCP + REST · Audit log on every plan