It gives agents a structured place to query and modify recorded runs instead of keeping results only in files.

dolt_runs — MCP server by swarm-ai-research/swarm

dolt_runs

dolt_runs is an MCP server for Claude Code, Codex, Cursor, Gemini CLI, OpenCode from swarm-ai-research/swarm. Its token cost is not measured, scanned A, original, MIT.

A connection to Dolt, a database that combines SQL tables with Git-like version history. It is configured as an MCP server for storing or retrieving experiment runs.

In plain words

What is it for?: Use it to work with experiment-run data in a local Dolt database.
Why use it?: It gives agents a structured place to query and modify recorded runs instead of keeping results only in files.

Written for no agent in particular: it speaks MCP, so any client can run it. Also seen: listed in a Claude config.

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/raelisavitt/go/bin/dolt-mcp-server.

One of 4 entries in .mcp.json upstream. Installing this one merges just its entry into your config; the other 3 are separate, each on its own page.

Good fit Use it to work with experiment-run data in a local Dolt database.

Compare 6 mcp servers from other repositories ↓

Installing this writes the configuration, not the program: `/Users/raelisavitt/go/bin/dolt-mcp-server` has to be on your PATH already, or the server will not start.

Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

Installing this writes the configuration, not the program: `/Users/raelisavitt/go/bin/dolt-mcp-server` has to be on your PATH already, or the server will not start.

Made for: Claude Code, Codex, Cursor, Gemini CLI, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/mcp/swarm-ai-research/swarm/dolt_runs/github.svg)](https://agentmods.dev/mcp/swarm-ai-research/swarm/dolt_runs)

Your own site

<a href="https://agentmods.dev/mcp/swarm-ai-research/swarm/dolt_runs"><img src="https://agentmods.dev/badge/mcp/swarm-ai-research/swarm/dolt_runs/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/mcp/swarm-ai-research/swarm/dolt_runs"><img src="https://agentmods.dev/badge/mcp/swarm-ai-research/swarm/dolt_runs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

dolt_runs scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.mcp.json · 14 lines

What it actually says

{
  "dolt_runs": {
    "command": "/Users/raelisavitt/go/bin/dolt-mcp-server",
    "args": [
      "--stdio",
      "--dolt-host",
      "127.0.0.1",
      "--dolt-port",
      "3307",
      "--dolt-user",
      "root"
    ]
  }
}

Same file

What else `.mcp.json` configures

This page is one entry in a file that holds 4. Installing the file brings all of them; each is measured and scanned on its own page.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 14 lines scan A e5a713b01461

Subscribe to this mod's changes

dolt_runs is an MCP server published in the GitHub repository swarm-ai-research/swarm (49 stars, last pushed 2d ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Databases Scientific agi-safety ai ai-agent ai-agents clawxiv openclaw

dolt_runs next to 6 mcp servers from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
dolt_runsswarm-ai-research/swarm	MCP server	49	2d ago	MIT	A	—	Claude Code, Codex, Cursor, Gemini CLI, OpenCode
apple-health-mcpsmarzola/apple-health-mcp	MCP server	3	4mo ago	MIT	A	—	Claude Code, Codex, Cursor, Gemini CLI, OpenCode
physionet-mcprafiattrach/physionet-mcp	MCP server	10	10mo ago	MIT	A	—	Claude Code, Codex, Cursor, Gemini CLI, OpenCode
docs-langchainlangchain-ai/langchain	MCP server	149k	today	MIT	A	—	Claude Code, Codex, Cursor, Gemini CLI, OpenCode
component-explorermicrosoft/vscode	MCP server	195k	today	MIT	A	—	Claude Code, Codex, Cursor, Gemini CLI, OpenCode
codex_message_boardopenai/codex	MCP server	134k	today	Apache-2.0	A	—	Claude Code, Codex, Cursor, Gemini CLI, OpenCode
playwright-testmicrosoft/playwright	MCP server	99k	today	Apache-2.0	A	—	Claude Code, Codex, Cursor, Gemini CLI, OpenCode