Fractal Process Intelligence

io.github.chevy155Published by GitHub account chevy155v0.1.1Updated Oct 24, 2026

Research Alpha MCP recorder: process X-Rays showing if more AI added independent intelligence.

VerifiedStreamable HTTPWeb executableKnowledge & MemoryData & Analytics

Overview

AI-generated overview

A remote recorder that lets an assistant log a research run's agents, sources, claims and tool use, then compiles a hosted process X-Ray report.

What you can do
Open and close a research run, producing a hosted X-Ray report URL at the end of the run (fractal_start_run, fractal_finish_run). Record participating agents and their optional metadata. Record cited sources together with their lineage. Record claims with their stance, plus uncertainty and disagreement. Record tool-call evidence from the run.
When to use it
Useful when you want an observable record of how a research answer was assembled, rather than only the polished final answer, and want to compare that process across runs or agents. It is an active research experiment, so treat it as exploratory rather than a validated product.
Requirements
A remote MCP endpoint; no local package is declared. The README's Claude Desktop example connects through npx with the mcp-remote bridge, so Node.js is needed for that setup path. No provider API keys or environment variables are declared.
Before you install
Runs are recorded only when the tools are explicitly invoked, so avoid starting a run in ordinary chats. Recorded artifacts are sent to a third-party hosted service that generates the report. It does not call AI models or buy inference, and it does not inspect hidden reasoning.

Installation

In SourceWeft

  1. Open Fractal Process Intelligence in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.chevy155%2Ffractal-process-intelligence-mcp/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "fractal-process-intelligence": {
      "type": "http",
      "url": "https://mcp.fractalinfinity.io/mcp"
    }
  }
}

README

Fractal Process Intelligence — Research Alpha

Fractal measures whether additional AI actually created additional intelligence.

Fractal is not trying to make AI smarter. It observes research process and produces an X-Ray of what a polished final answer may hide.

Primary question: Did additional AI actually create additional independent intelligence?

This repository is the public distribution surface for the Fractal Research MCP (recorder/observer). The live remote endpoint is already hosted; this repo documents how to connect and give feedback.

Research Alpha: This is an active research experiment, not a validated commercial product.

What it does

Fractal Process Intelligence MCP is recorder/observer only.

Compatible AI clients can record observable research-process artifacts:

  • participating agents
  • meaningful sources
  • claims
  • uncertainty
  • disagreement
  • tool usage

Then finish_run compiles a process X-Ray (hosted report URL).

Public product page: fractalinfinity.io/research-lab.html
Sample X-Ray: fractalinfinity.io/report/sample.html

What it does NOT do

  • Call AI models (no Anthropic / OpenAI / Gemini inference)
  • Buy model inference on your behalf
  • Require provider API keys
  • Inspect hidden chain-of-thought
  • Automatically spawn agents
  • Estimate Claude/OpenAI billing or token dollar cost

Health check advertises "inference":"none".

Public MCP endpoint

text
https://mcp.fractalinfinity.io/mcp

Health: https://mcp.fractalinfinity.io/health

Current recorder tools

ToolPurpose
fractal_start_runOpen a run
fractal_record_agentRecord agent identity / optional metadata
fractal_record_sourceRecord a cited source + lineage
fractal_record_claimRecord claim stance
fractal_record_toolRecord tool-call evidence
fractal_finish_runFinalize → X-Ray URL

Claude Desktop (Windows) alpha setup

  1. Claude Desktop → Settings → Developer → Edit Config
  2. Merge the MCP entry below (do not wipe other config keys).
  3. Save.
  4. Fully quit Claude (system tray → Quit).
  5. Reopen Claude.
  6. Settings → Developer should show fractal-process-intelligence running.
json
{  "mcpServers": {    "fractal-process-intelligence": {      "command": "C:\\Program Files\\nodejs\\npx.cmd",      "args": [        "-y",        "mcp-remote",        "https://mcp.fractalinfinity.io/mcp"      ]    }  }}

See also: examples/claude-desktop.mcp.fragment.json

Microsoft Store builds of Claude may store config under a package LocalCache path; prefer Edit Config so Claude opens the file it actually reads. Use the full npx.cmd path on Windows.

Example research instruction

Paste into a new research conversation after connecting:

text
Use Fractal Process Intelligence to record this research run.
Record the participating agents, meaningful sources, important claims,uncertainty, disagreement and significant tool usage.
Finish the run and return the Fractal X-Ray URL.
Do not interpret the X-Ray for me before I open it.

Then ask your normal research question. Read the AI’s final answer first. Open the X-Ray second.

Privacy / security boundary

Fractal records only artifacts explicitly sent through its MCP tools.

It does not automatically record every Claude (or other) conversation. For normal chats, do not start a Fractal run / do not invoke its tools.

Feedback (the research question)

Open a GitHub Issue or reply in discussions.

Please answer:

  1. Did the X-Ray reveal something consequential you would not have known from the final AI answer alone?
  2. Would you want this attached to your normal research or agent workflow?

Optional: what was confusing or misleading?

Links

ResourceURL
Research Labhttps://fractalinfinity.io/research-lab.html
Sample X-Rayhttps://fractalinfinity.io/report/sample.html
MCP endpointhttps://mcp.fractalinfinity.io/mcp
Healthhttps://mcp.fractalinfinity.io/health

License

MIT — see LICENSE.

Source: README.md at commit 3ff9b0a

Tools

6

fractal_start_run

Fractal Research MCP recorder tool: fractal_start_run

Takes no parameters.

fractal_record_agent

Fractal Research MCP recorder tool: fractal_record_agent

Takes no parameters.

fractal_record_source

Fractal Research MCP recorder tool: fractal_record_source

Takes no parameters.

fractal_record_claim

Fractal Research MCP recorder tool: fractal_record_claim

Takes no parameters.

fractal_record_tool

Fractal Research MCP recorder tool: fractal_record_tool

Takes no parameters.

fractal_finish_run

Fractal Research MCP recorder tool: fractal_finish_run

Takes no parameters.

Version history

1
  1. v0.1.1LatestSep 16, 2026

Score

100% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts