FreeHow credits work →

Research tools for CodeBuddy

One codebuddy mcp add command in CodeBuddy Code, or one entry in the MCP tab of CodeBuddy IDE. After a browser sign-in, CodeBuddy can fetch statistics, datasets and discipline records for your scripts.

Connect your agentSee all capabilities
ClaudeCodexChatGPTCursorGemini CLIAntigravityWorkBuddyTraeCodeBuddyCherry StudioQoderQwen CodeKimi Code

How to connect ScholarMuse to CodeBuddy

CodeBuddy Code takes one command; CodeBuddy IDE takes one entry in its MCP tab. CodeBuddy Code can run shell commands, so pasting “Read https://scholarmuse.ai/install/agent.md and follow the instructions to connect ScholarMuse” into it should also work. These steps follow the CodeBuddy documentation.

Full connect guide →

  1. Step 1

    CodeBuddy Code: run one command

    Run this in a terminal. It adds ScholarMuse to your user configuration, the file ~/.codebuddy/.mcp.json, so it is available in every project.

    codebuddy mcp add --scope user --transport http scholarmuse https://scholarmuse.ai/mcp

  2. Step 2

    CodeBuddy IDE: add an MCP entry

    Open CodeBuddy Settings at the top right of the chat panel, go to the MCP tab, choose Add MCP and paste this JSON.

    {
  "mcpServers": {
    "scholarmuse": {
      "type": "http",
      "url": "https://scholarmuse.ai/mcp"
    }
  }
}

  3. Step 3

    Start the sign-in

    In CodeBuddy Code, type /mcp to see the server status and authorize scholarmuse from there.

  4. Step 4

    Approve in your browser

    A scholarmuse.ai window opens. Sign in, approve access and choose which discipline packs CodeBuddy may use. There is no API key to create or paste.

  5. Step 5

    Check that it works

    Type /mcp again and check that scholarmuse shows as connected, then ask CodeBuddy to list the ScholarMuse capabilities.

What CodeBuddy can pull into your project

CodeBuddy works in a terminal or an editor, close to your scripts. The list favours records that end up as files in the project: series, dataset metadata, structures, catalogues and trial registrations.

Economic & social statistics

Economic & social statistics

All disciplines · FRED, World Bank, IMF +5

Find datasets

Find datasets

All disciplines · DataCite, Zenodo, Dryad +2

Search papers

Search papers

All disciplines · OpenAlex, PubMed / Europe PMC, arXiv +5

Protein structures

Protein structures

Life sciences & medicine · RCSB PDB, AlphaFold DB

Earthquake & water data

Earthquake & water data

Earth & environment · USGS

Clinical trials search

Clinical trials search

Life sciences & medicine · ClinicalTrials.gov

Exoplanets & stars

Exoplanets & stars

Astronomy · NASA Exoplanet Archive, Gaia Archive, SIMBAD

Economic & social statistics
Fetch an official series once and commit it with its source, so a colleague who reruns the script gets the same numbers.
Find datasets
Search DataCite, Zenodo, Dryad, Harvard Dataverse and Hugging Face from the command line and record the DOI in your data README.
Search papers
Collect the papers a replication is based on, with DOIs, into a references file next to the code.
Protein structures
Get an experimental structure from RCSB PDB or a predicted one from AlphaFold DB, then analyse it with your own script.
Earthquake & water data
USGS earthquakes around a point for a period you specify (up to 200 events per call) and stream-gauge readings, ready for analysis code.
Clinical trials search
Pull registrations from ClinicalTrials.gov by condition, intervention, phase and status into a table for an evidence review.
Exoplanets & stars
Query the NASA Exoplanet Archive and the Gaia catalogue and plot the result in the same session.

Things to ask CodeBuddy

Earthquake & water data

You say to your agent

Use ScholarMuse to get the 200 largest earthquakes since 2008 within 400 km of 31.0 N, 103.4 E. Save the catalogue as CSV and plot magnitude against depth.

A USGS catalogue with time, location, depth and magnitude that CodeBuddy saves and plots.

Protein structures

You say to your agent

Fetch the experimental structure 6LU7 and write a Biopython script that lists the residues within 4 Å of the bound inhibitor.

The structure record and file from RCSB PDB, with the script written against it.

Clinical trials search

You say to your agent

List phase 3 trials of GLP-1 receptor agonists for obesity that are recruiting or completed. Export registration number, sponsor, enrolment and primary outcome to a spreadsheet.

Matching ClinicalTrials.gov registrations that CodeBuddy writes to a file for screening.

Frequently asked questions

In CodeBuddy Code, yes in principle: it can run shell commands, so you can paste “Read https://scholarmuse.ai/install/agent.md and follow the instructions to connect ScholarMuse”. It runs the add command and you only complete the sign-in in your browser.

The entry you add contains the server name, the transport type and the address, nothing else. ScholarMuse has no API key. Access is granted through the browser sign-in at scholarmuse.ai.

No. Both connect to the same address and you sign in with the same ScholarMuse account. Each one is added and authorized on its own, with the steps above.

Discipline tools belong to discipline packs, and CodeBuddy sees only the packs you allowed during authorization. Allow the life sciences or earth and environment pack in your ScholarMuse account, then ask CodeBuddy to list the capabilities again.

Every call your agent makes uses credits, and a call is charged only when it succeeds. There are no subscriptions. A new account starts with a one-time gift of 50 credits. The 6 web tools under /tools are free without an account, up to 5 runs a day.

Requests are used only to answer you. We do not train models on them.

Ready to make your agent a better scholar?

Connect once. Papers, data and figures from 50+ sources, in the agent you already use.

Works with compatible AI agents

ClaudeChatGPTCodexCursorWorkBuddyTraeGemini CLIAntigravityQoderCodeBuddyKimi CodeQwen CodeClineKiroWindsurfZedOpenCodeOpenClawDifyCherry StudioLM StudioGooseAmpContinueRoo CodeVS CodeJetBrainsWarpRaycastCopilotPerplexityAny MCP client

Data from OpenAlex · Crossref · PubMed · arXiv · NIH · UniProt · PDB · PubChem · NASA · World Bank · USGS · GBIF and more