HumanMirror Forge

fr.humanmirrorPublished by humanmirror.frOfficial publisherv1.0.1Updated Oct 24, 2026

Five deterministic micro-tools for AI-agent data pipelines: clean, dedupe, normalize, score, detect.

The publisher's own server: HumanMirror Flow

VerifiedStreamable HTTPWeb executableDeveloper Tools Data & Analytics

Server details

Identifier: fr.humanmirror/forge
Transport: Streamable HTTP
Runtime: Web executable
Trust: Verified
Published: Sep 16, 2026

Security note

MCP servers receive tool arguments from a conversation and may perform external actions. Review what a server can do before you enable it, and give it only the access it needs.

The registry verified that this server's namespace belongs to humanmirror.fr, which also runs its endpoint. That identifies the publisher; it does not make the server's tools safe.

SourceWeft's checks cover whether the listing is complete and the endpoint answered; they do not review the server's code or what its tools do.

Add a badge to your README

Show readers this MCP server is listed on SourceWeft. The badge links to this page.

[![Listed on SourceWeft](https://sourceweft.com/badge/mcp/fr.humanmirror%2Fforge.svg)](https://sourceweft.com/mcp/fr.humanmirror%2Fforge?utm_source=readme&utm_medium=badge)

Overview

AI-generated overview

Remote MCP server offering five deterministic data-cleaning micro-tools for AI-agent pipelines: clean JSON, dedupe records, normalize entities, score quality…

What you can do: Clean and stabilize JSON: trim strings, normalize and sort keys, optionally drop empty values
Remove duplicate JSON records by exact canonical match or selected key fields
Normalize entity names, domains, URLs and emails into canonical machine-readable values
Score record arrays on completeness, duplicate rate and field type consistency
Detect numeric outliers with IQR and robust summary statistics, returning anomaly positions
When to use it: Useful when an assistant works with messy record arrays and needs repeatable, deterministic cleanup steps before analysis or loading: standardizing JSON, removing duplicates, canonicalizing entities, judging data quality, or flagging outliers.
Requirements: A remote streamable HTTP endpoint at humanmirror.fr; no local package. Requires a HumanMirror Forge API key sent as a bearer token in the Authorization header. Each successful tool call consumes one Forge credit, so an account with credits is needed.

Before you install

Every successful call spends one HumanMirror Forge credit, so repeated or automated use costs money. The API key is passed in the Authorization header and should be kept secret. Record data you submit is processed by a third-party remote service.

Installation

In SourceWeft

Open HumanMirror Forge in the dashboard and add it to a workspace.
Connect Authorization token credentials. They are stored privately and never shown on public pages.
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/fr.humanmirror%2Fforge/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": {
    "humanmirror-forge": {
      "type": "http",
      "url": "https://humanmirror.fr/api/forge/mcp/",
      "headers": {
        "Authorization": "Bearer <YOUR_TOKEN>"
      }
    }
  }
}

README

This repository has no README.

Tools

clean_json

Normalize JSON deterministically: trim strings, normalize object keys, optionally remove empty values, and sort keys for stable downstream processing. One successful call consumes 1 HumanMirror Forge credit.

Parametersinputrequiredoptions

dedupe_records

Remove duplicate JSON records using exact canonical matching or selected key fields. One successful call consumes 1 HumanMirror Forge credit.

Parametersinputrequiredoptions

normalize_entity

Normalize entity names, domains, URLs and emails into stable machine-readable canonical values. One successful call consumes 1 HumanMirror Forge credit.

Parametersinputrequired

score_data_quality

Score record-array data quality using completeness, duplicate rate and field type consistency. One successful call consumes 1 HumanMirror Forge credit.

Parametersinputrequired

detect_anomaly

Detect numeric outliers using IQR and robust summary statistics, returning machine-readable anomaly positions. One successful call consumes 1 HumanMirror Forge credit.

Parametersinputrequired

Version history

v1.0.1LatestOct 9, 2026
v1.0.0Sep 16, 2026

Score

75% 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
Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.
License10 pts
Declare a license in the repository or the registry entry.