Carbon Forge

io.github.100monkeys-aiPublished by GitHub account 100monkeys-aiv1.0.0Updated Oct 24, 2026

One record of code, files and pages that people and agents read and write, with lanes and git.

The publisher's own server: Carbon Fyi

VerifiedStreamable HTTPWeb executableWeb Search & ScrapingKnowledge & MemoryDeveloper Tools

Overview

AI-generated overview

Lets an assistant read, search and browse a shared workspace of pages, atoms and code trees, with revisions, comments and cross-links.

What you can do
It exposes a workspace of pages and atoms as Markdown, with tools to list and read them by path or UUID, optionally returning a single heading section. Search is available both as hybrid full-text plus vector retrieval and as exact-substring matching. It also lists revisions and diffs them, reads comments and media metadata, follows cross-links and semantic neighbors, browses code trees and the workspace file tree, and reports instance and workspace grounding.
When to use it
Use it when an assistant needs to consult or maintain a shared body of documentation, notes or code records that people and agents both edit. It fits retrieval over a known workspace, checking revision history or comments, and navigating code trees and file layouts. It is less suited to one-off public web lookups.
Requirements
A remote streamable HTTP endpoint at carbonforge.dev; nothing to install locally. An optional Authorization header carrying a bearer token from settings or API tokens is required to write or read private content; without it the endpoint serves public workspaces read-only. Network access to the endpoint is needed.
Before you install
The Authorization header is a bearer token; without it the endpoint is read-only and public, with a token needed to write or read private content. A token may grant write access to workspace content, so treat it as a secret and prefer a scoped token. Some tools are viewer-aware and expose only what the caller may see, but listing workspaces is a membership catalogue and not a capability check.

Installation

In SourceWeft

  1. Open Carbon Forge 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.100monkeys-ai%2Fcarbon-forge/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": {
    "carbon-forge": {
      "type": "http",
      "url": "https://carbonforge.dev/api/mcp"
    }
  }
}

Tools

22

pages.list

List pages in a workspace. `path_prefix` narrows by leading segment; `body_contains` keeps pages whose Markdown holds a literal substring; `metadata` keeps pages whose top-level metadata contains the given scalar keys; `sort` (path | updated_at | created_at) and `direction` order the set; `include_metadata` adds each page's metadata. Details: https://carbonforge.dev/docs/p/api/mcp-tools-catalog

Parameterssortlimitcursorinstancemetadatadirectionworkspacepath_prefixbody_containsinclude_metadata

pages.read

Read a page by path or UUID. Returns the Markdown body plus the page metadata object. Pass `section` with a heading's plain text to get back only that heading and the blocks under it, down to the next heading at the same or shallower level; the result then also carries `section: { heading, level, matches }`. Details: https://carbonforge.dev/docs/p/api/mcp-tools-catalog

ParameterslanesectioninstancepathOrIdrequiredworkspace

atoms.list

List atoms in the current workspace. The `path_prefix`, `body_contains`, `metadata`, `sort`, `direction` and `include_metadata` arguments mirror the same arguments on pages.list.

Parameterssortlimitcursorinstancemetadatadirectionworkspacepath_prefixbody_containsinclude_metadata

atoms.read

Read an atom by path or UUID with usage_pages projection. Returns metadata. Pass `section` with a heading's plain text to get back only that heading and the blocks under it, down to the next heading at the same or shallower level; the result then also carries `section: { heading, level, matches }`, and everything else on it is the atom's own, so a section can be read and written straight back.

ParameterslanesectioninstancepathOrIdrequiredworkspace

search.global

Hybrid FTS + pgvector + RRF search. Returns Markdown excerpts.

Parametersqrequiredlimitscopecursorinstanceworkspaceperspective

search.literal

Exact-substring search over the Markdown projection of pages and atoms — deterministic, unlike hybrid `search.global`. A needle shorter than 3 characters is rejected. Returns one envelope per matched entity, up to 5 hits each as `{ line, col, snippet }`. `case_sensitive` defaults to false; `scope` is workspace | all_mine | all_public. Details: https://carbonforge.dev/docs/p/api/mcp-tools-catalog

Parametersqrequiredkindslimitscopecursorinstanceworkspacecontext_linescase_sensitive

discovery.list_entities

Browse pages or atoms inside a workspace with faceted filters (tag, author, date range, visibility, metadata containment) and sort by alphabetical, recency, or star count. Viewer-aware: members see everything, anonymous callers see only public entities in public workspaces. 50 items per page, cursor-based. Details: https://carbonforge.dev/docs/p/api/mcp-tools-catalog

Parametersqkindrequiredsortlimitcursorfiltersinstanceworkspaceworkspace_idworkspace_slug

revisions.list

List revisions for a page or atom (cursor-paginated).

ParameterskindrequiredlimitcursorinstancepathOrIdrequiredworkspace

revisions.get

Fetch a specific revision (returns Markdown body).

ParameterskindrequiredinstancepathOrIdrequiredworkspacerevision_idrequired

revisions.compare

Markdown-level diff between two revisions of the same page or atom. Returns segments (op: equal | insert | delete) plus both Markdown projections.

ParameterskindrequiredinstancepathOrIdrequiredworkspacerevision_a_idrequiredrevision_b_idrequired

media.read

Fetch metadata for a single media item.

Parametersinstancemedia_idrequiredworkspace

comments.list

List the comment thread for a page or atom.

Parametersinstanceworkspacetarget_kindrequiredtarget_pathOrIdrequired

cortex.ground

Orientation surface: instance metadata, both grounding documents, identity and capabilities, reachable workspaces, sidecar health. Pass `workspace` to ground a named workspace without moving the per-token pointer. Pass a `known_grounding_at` / `known_workspace_grounding_at` you hold and an unchanged document is acknowledged, not resent. Details: https://carbonforge.dev/docs/p/api/mcp-tools-catalog

Parametersinstanceworkspaceknown_grounding_atknown_workspace_grounding_at

workspaces.list

List every workspace the calling user is a member of. This is a membership catalogue and not a capability: it is not narrowed by the token, so a listed workspace may still be outside this token's reach. Call cortex.ground for what this token can actually resolve.

Takes no parameters.

workspaces.resolve_slug

Resolve a workspace slug to its id, role, and archived state. 404 when the caller isn't a member (no enumeration).

Parametersslugrequiredinstance

discovery.list_instances

List instances. Filter: all (default) | public | my | my_admin. public lists an instance that has public reading on, is listed in Discover, is not frozen, and has a workspace that is not private holding a page that is not private. my and my_admin list the caller's own instances (member; admin) with no such gate; all is public plus my. Without a token every filter is public.

Parameterslimitqueryfilter

discovery.list_workspaces

List workspaces across one or all instances, with the same filters. public lists a workspace when its instance has public reading on, the workspace is not private, its instance is listed in Discover and not frozen, and it holds a page that is not private. my and my_admin list the caller's own workspaces with no such gate; all is public plus my. Without a token every filter is public.

Parameterslimitqueryfilterinstance_id

trees.get

Read a code tree's revision (the current one by default), its metadata and surface, and a page of its entries in path order: path, git mode, size and blob SHA-256, optionally under `path_prefix`. A symlink's blob is its target; a submodule link has no blob and gives its `commit`. With `lane`, `metadata` is the lane's bag if it sets one. Anonymous callers read a public code tree's current one.

Parameterslanelimitoffsetinstanceworkspacepath_or_idrequiredpath_prefixrevision_idsnapshot_id

files.list

Browse the workspace as a file tree, one level at a time: directories, pages, atoms, code trees (expanded at their paths) and library entries. Each node names its kind, entity, current revision and digest; `at` holds the entities exactly at `path`. `surface` keeps that surface only. History: files.history. Anonymous callers see public pages and atoms, and code trees of surface code.

Parameterslanepathlimitoffsetsurfaceinstanceworkspaceperspective

Version history

1
  1. v1.0.0LatestOct 24, 2026

Score

83% 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.

  • LicenseNot applicable

    A hosted service is used under its provider's terms, so no license is expected here. This check is left out of the percentage.

Other Carbon integrations

Carbon Fyi

fyi.carbonOfficial publisher

Read-only, keyless access to carbon.fyi's curated voluntary carbon market news archive and open carbon price data.

Streamable HTTPWeb executable
Web Search & Scraping6 toolsOct 24, 2026

CARBON

Published by GitHub account jarbon

CARBON Core's MCP server gives a coding agent a risk-based AI testing harness with local evidence reports, run through the Jay test-manager persona.

STDIODesktop only
Browser Automation6 toolsNov 5, 2026

Carbon

Published by GitHub account CarbonDataSolutions

Carbon connects an AI assistant to the carbon.talent data and AI hiring platform so you can search talent, draft and post roles, and move applicants through…

Streamable HTTPWeb executableAuth
Productivity & WorkflowCredential requiredOct 29, 2026

Carbon

Published by GitHub account danie-carbondatasolutions

Carbon connects an AI assistant to the carbon.talent hiring platform so you can search data and AI talent, post roles, and move applicants through stages.

Streamable HTTPWeb executable
Productivity & WorkflowNot indexed yetOct 5, 2026

Testers.ai CARBON Test Harness Lite

Published by GitHub account jarbon

Local QA test harness that gives AI coding agents bounded software testing workflows, screenshot maps and evidence-qualified confidence reports.

STDIODesktop only
Browser AutomationNot validated yetNov 1, 2026