MCP server

Use Easy Can Do from your coding agent.

Easy Can Do is a checked catalog of 1,264 AI models, APIs, data feeds and apps. Its MCP server lets a coding agent search the catalog while it builds, instead of searching the web.

An example
You

Add voice memo transcription to my notes app.

search_toolsquery: "transcribe audio", have: "sound", want: "words"

  • ElevenLabs Scribe

    Transcribe audio with speakers labeled and laughter or applause tagged.

    Official API · $
  • Deepgram

    Transcribe speech live and know when the speaker has finished talking.

    Official API · $
  • Parakeet

    Transcribe audio into subtitles very fast on your own Mac.

    Official API · free · runs locally

get_toolslugs: ["elevenlabs-scribe"]

Set up

Give your agent one prompt and it adds Easy Can Do for you.

1

Pick your agent

2

Paste this into Claude Code

Add the Easy Can Do MCP server for me. Run claude mcp add easycando --scope user --transport http https://easycando.com/mcp. Then tell me to start a new session and run /mcp to check that it’s connected.

Or set it up yourself

Run this once in a terminal. It adds Easy Can Do to every project.

claude mcp add easycando --scope user --transport http https://easycando.com/mcp

Then start Claude Code and run /mcp to check that it’s connected.

Server details
Server URL
https://easycando.com/mcp
Transport
Remote Streamable HTTP. Read-only.
Account
None. No key and no sign-in.
Limit
300 calls an hour from one address.

Tools

  • search_tools

    Finds tools for one step of a build. Give a short query, and have and want when you know what goes in and what should come out. Returns up to 10 previews, each with the capability that matched, its API status, price tier and page link.

  • get_tool

    The full record of up to 5 tools. It lists each capability with its price and limits, access and auth, ways in, docs and pricing links, terms, and the date it was checked.

  • find_chains

    Finds tools that turn one kind of input into another, alone or two in a row.

How an agent uses it

  1. 1Split the build into steps. Call search_tools once per step.
  2. 2Call get_tool on the picks before writing integration code.
  3. 3When no single tool does a step, call find_chains.
  4. 4Tell the user which tool it picked and why, and link the tool’s page.

Without the MCP

Every tool page has a markdown copy: add .md to its address, as in https://easycando.com/tools/deepgram.md. The index for agents is https://easycando.com/llms.txt.

Privacy

The server keeps no query text. It logs the tool name, the number of results and the time taken. The hourly limit counts calls under a salted hash of the address, which expires within two hours.

Made by Jasper Burns

A short note when I ship something new, about once a month. One list for all my projects.