Skip to main content

Carbon Forge

io.github.100monkeys-ai/carbon-forgeVersion 1.0.0

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

Status

Responds1609 msAnswered our handshake without sign-in.

Registry data may be out of date

We could not refresh it, so this page shows the last copy.
Last checked
Nov 14, 2026, 14:34 UTC
Latency
1609 ms
Remotes responding
1 of 2
Sign-in
API key, No sign-in
Hosting
Hosted outside the EU (detected)
Registry data as of
Nov 14, 2026, 22:14 UTC

Data from the official MCP Registry, checked by run.zero. How we check

Connect

Streamable HTTP
https://carbonforge.dev/api/mcpResponds1609 ms
No sign-in

Claude Code

claude mcp add --transport http carbon-forge https://carbonforge.dev/api/mcp

Claude Desktop and claude.ai

Settings > Connectors > Add custom connector
Name: carbon-forge
Remote MCP server URL: https://carbonforge.dev/api/mcp

Cursor

{
  "mcpServers": {
    "carbon-forge": {
      "url": "https://carbonforge.dev/api/mcp"
    }
  }
}

VS Code

code --add-mcp '{"name":"carbon-forge","type":"http","url":"https://carbonforge.dev/api/mcp"}'
Streamable HTTP
https://{instance}.carbonforge.dev/api/mcpNot checked

Claude Code

claude mcp add --transport http carbon-forge 'https://<YOUR_INSTANCE>.carbonforge.dev/api/mcp' --header 'Authorization: Bearer <YOUR_TOKEN>'

Replace <YOUR_INSTANCE>, <YOUR_TOKEN> before running.

Claude Desktop and claude.ai

Settings > Connectors > Add custom connector
Name: carbon-forge
Remote MCP server URL: https://<YOUR_INSTANCE>.carbonforge.dev/api/mcp
This server expects the header Authorization.

Replace <YOUR_INSTANCE> before running.

Cursor

{
  "mcpServers": {
    "carbon-forge": {
      "url": "https://<YOUR_INSTANCE>.carbonforge.dev/api/mcp",
      "headers": {
        "Authorization": "Bearer <YOUR_TOKEN>"
      }
    }
  }
}

Replace <YOUR_INSTANCE>, <YOUR_TOKEN> before running.

VS Code

code --add-mcp '{"name":"carbon-forge","type":"http","url":"https://<YOUR_INSTANCE>.carbonforge.dev/api/mcp","headers":{"Authorization":"Bearer <YOUR_TOKEN>"}}'

Replace <YOUR_INSTANCE>, <YOUR_TOKEN> before running.

Built your own server? run.zero hosts MCP servers on European infrastructure.

Host your own MCP server on run.zero

Tools

22 tools

Tools of Carbon Forge
Read-only
Idempotent
Open world
atoms.listList atoms in the current workspace. The `path_prefix`, `body_contains`, `metadata`, `sort`, `direction` and `include_metadata` arguments mirror the same arguments on pages.list.Not declaredYesNot declaredNot declared
atoms.readRead 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.Not declaredYesNot declaredNot declared
comments.listList the comment thread for a page or atom.Not declaredYesNot declaredNot declared
cortex.groundOrientation 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-catalogNot declaredYesNot declaredNot declared
discovery.list_entitiesBrowse 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-catalogNot declaredYesNot declaredNot declared
discovery.list_instancesList 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.Not declaredYesNot declaredNot declared
discovery.list_workspacesList 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.Not declaredYesNot declaredNot declared
discovery.searchSearch instance and workspace metadata + grounding documents. Returns parallel lists for both scopes.Not declaredYesNot declaredNot declared
files.listBrowse 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.Not declaredYesNot declaredNot declared
kg.get_relatedSemantic nearest-neighbors via similarity_edges.Not declaredYesNot declaredNot declared
kg.list_cross_linksList incoming + outgoing cross-links for a page or atom.Not declaredYesNot declaredNot declared
media.readFetch metadata for a single media item.Not declaredYesNot declaredNot declared
pages.listList 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-catalogNot declaredYesNot declaredNot declared
pages.readRead 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-catalogNot declaredYesNot declaredNot declared
revisions.compareMarkdown-level diff between two revisions of the same page or atom. Returns segments (op: equal | insert | delete) plus both Markdown projections.Not declaredYesNot declaredNot declared
revisions.getFetch a specific revision (returns Markdown body).Not declaredYesNot declaredNot declared
revisions.listList revisions for a page or atom (cursor-paginated).Not declaredYesNot declaredNot declared
search.globalHybrid FTS + pgvector + RRF search. Returns Markdown excerpts.Not declaredYesNot declaredNot declared
search.literalExact-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-catalogNot declaredYesNot declaredNot declared
trees.getRead 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.Not declaredYesNot declaredNot declared
workspaces.listList 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.Not declaredYesNot declaredNot declared
workspaces.resolve_slugResolve a workspace slug to its id, role, and archived state. 404 when the caller isn't a member (no enumeration).Not declaredYesNot declaredNot declared

Details

Registry status
Active
Published
Oct 23, 2026
Updated
Oct 23, 2026
Repository
Not given
Categories (suggested)
Developer toolsSearch and webSuggested categories are assigned automatically from the registry text and may be wrong. Verified operators can correct them.
GDPR
Not declared

Are you the operator? Claim this listing