About RealRun
RealRun is a read-only MCP server for published results from independent AI model tests on five everyday task types. Agents can compare scores and safety warnings to choose a model based on accuracy, cost, or a balance of both.
Key features
- 01List tested tasks and result details
- 02Compare model scores by task
- 03Get accuracy-, cost-, or balanced recommendations
- 04Retrieve safety and caution flags
Use cases
- 01Choose a model for inbox triage
- 02Compare models for meeting scheduling
- 03Select a model for receipts or finance tasks
- 04Review cautions before using a model for support replies
MCP support
RealRun exposes read-only task, score, recommendation, and warning lookups to MCP clients. It is available as a remote Streamable HTTP endpoint or can run locally over stdio.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://realrun.baseledgerip.com/mcpclaude mcp add --transport http com-baseledgerip-realrun-realrun https://realrun.baseledgerip.com/mcp{"mcpServers":{"com-baseledgerip-realrun-realrun":{"type":"http","url":"https://realrun.baseledgerip.com/mcp"}}}Open in Cursor{"servers":{"com-baseledgerip-realrun-realrun":{"type":"http","url":"https://realrun.baseledgerip.com/mcp"}}}Open in VS Code{"mcpServers":{"com-baseledgerip-realrun-realrun":{"type":"http","url":"https://realrun.baseledgerip.com/mcp"}}}{"mcpServers":{"com-baseledgerip-realrun-realrun":{"serverUrl":"https://realrun.baseledgerip.com/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
4This tool takes no parameters.
Details
From the project READMERealRun MCP server
Read-only lookups over RealRun's published, independent tests of AI models on everyday tasks (inbox triage, meeting scheduling, receipts, small-business finance, customer support replies). It lets an agent ask "which model should I use for task X?" and get scores and safety warnings back.
Connect (remote, no install)
Streamable HTTP endpoint: https://realrun.baseledgerip.com/mcp
{ "mcpServers": { "realrun": { "url": "https://realrun.baseledgerip.com/mcp" } } }
Claude Code: claude mcp add --transport http realrun https://realrun.baseledgerip.com/mcp
Cline: add this to cline_mcp_settings.json (keep "type": "streamableHttp"; without it Cline falls back to SSE and the connection fails). Full agent-readable steps: llms-install.md.
{ "mcpServers": { "realrun": { "type": "streamableHttp", "url": "https://realrun.baseledgerip.com/mcp", "disabled": false, "autoApprove": [] } } }
Run locally (stdio)
npx -y realrun-mcp
(once published to npm; from a checkout: npm install && node src/stdio.mjs)
Tools
| Tool | Input | Returns |
|---|---|---|
list_tasks | none | Tested tasks, item counts, dates, results pages, playbook prices |
get_scores | task | Every model's headline score (best first), cost tier, metric definition |
recommend_model | task, priority (accuracy/cost/balanced), include_subscription | One pick + 2 alternatives; never picks a model flagged not recommended |
get_warnings | task | Not-recommended and caution flags (scam failures, invented data, inconsistency) |
Task ids: inbox-triage, meeting-scheduling, receipts, finance, support-replies.
All tools are read-only. The server stores nothing and has no auth. It is stateless, with JSON responses.
Data
src/data.json holds only the published headline numbers. Full prompts and item-level results are in the paid playbooks ($29 each, links in list_tasks). Scores reflect our tests on the dates shown, not a guarantee.
Billing (not active)
Every call passes through src/metering.mjs. The plan is a free allowance of about 20 lookups a day, then per-call billing via Stripe or x402. It is off: nobody is charged, and no payment objects exist.
Test
npm test runs stdio end to end. node test/smoke.mjs https://realrun.baseledgerip.com/mcp tests the remote endpoint.
Layout
src/server.mjs: toolssrc/stdio.mjs: CLIsrc/http.mjs: exports for the HTTP function../netlify/functions/mcp.mjs: Netlify Function at/mcpserver.json: official MCP registry metadata
License: MIT. © Base Ledger IP LLC.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.