Carbon Forge

MCP server · hosted · v1.0.0 · io.github.100monkeys-ai/carbon-forge

Online · tested 2h agoNEW · 3h agoSeen in the registry 2h ago

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

What it does

Carbon Forge is an MCP server, a connector that lets an AI assistant use it as a tool. It is hosted: an assistant connects to it over the internet, nothing to install.

No capability identified yet from its description.

Facts come from the Official MCP Registry, as declared by the publisher. Capabilities are matched automatically (low confidence) and are not a test of the tool.

At a glance

Hosted (remote)YES

Local installNO

Live checkOnline · 22 tools

Version1.0.0

PriceNot in the registry

First seen24 Oct 2026

Last checked2h ago

How to connect

As declared in the Official MCP Registry · hosted endpoint tested by Electra Index 2h ago (live check)

Hosted endpoints

https://{instance}.carbonforge.dev/api/mcp streamable-http
https://carbonforge.dev/api/mcp streamable-http

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

The endpoint contains a placeholder to replace with your own value (see the publisher's docs).

Required: Authorization (get it from the publisher)

MCP settings (Claude Desktop, Cursor and other MCP clients)

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

Live check

Electra Index connected to the hosted endpoint 2h ago

ONLINE Carbon Forge answered an MCP connection on 24 Oct 2026 and introduced itself as carbon-forge bb9acf10c32d7d8d94b2f90ed00b0d4b97167220 (MCP protocol 2025-11-25).

22 tools offered to AI assistants

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 | update
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;
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.
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 resul
search.global · Hybrid FTS + pgvector + RRF search. Returns Markdown excerpts.
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, co
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 pub
kg.get_related · Semantic nearest-neighbors via similarity_edges.
kg.list_cross_links · List incoming + outgoing cross-links for a page or atom.
revisions.list · List revisions for a page or atom (cursor-paginated).
revisions.get · Fetch a specific revision (returns Markdown body).
revisions.compare · Markdown-level diff between two revisions of the same page or atom. Returns segments (op: equal | insert | delete) plus both Markdown projections.

Show 10 more

media.read · Fetch metadata for a single media item.
comments.list · List the comment thread for a page or atom.
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
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 toke
workspaces.resolve_slug · Resolve a workspace slug to its id, role, and archived state. 404 when the caller isn't a member (no enumeration).
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
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
discovery.search · Search instance and workspace metadata + grounding documents. Returns parallel lists for both scopes.
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
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

What "online" means: the server answered an MCP connection at the time of the check. It is not a guarantee of security, quality or continuous uptime. How we test: we open an MCP session and ask for the tool list, as an AI assistant would. We never run a tool and never send a key. Checked every few days. Method

Is this your server? Monitoring Pro: a check every 30 minutes and an email within the hour when it stops answering. Launch offer: $39.99 once, for life.

Facts & evidence

Each fact shows where it was seen and when.

Fact	Value	Evidence	Source	Last confirmed
Hosted endpoint	https://{instance}.carbonforge.dev/api/mcp, https://carbonforge.dev/api/mcp	DECLARED	SRC-001 Official MCP Registry	2h ago
Local install (package)	no	DECLARED	SRC-001 Official MCP Registry	2h ago
Remote access (hosted)	yes	DECLARED	SRC-001 Official MCP Registry	2h ago
Website	https://carbonforge.dev	DECLARED	SRC-001 Official MCP Registry	2h ago
Registry status	active	DECLARED	SRC-001 Official MCP Registry	2h ago
Version	1.0.0	DECLARED	SRC-001 Official MCP Registry	2h ago
MCP server	yes	DECLARED	SRC-001 Official MCP Registry	2h ago

Change history

NEW24 Oct 2026
first seen in the index

Is this page accurate?

Flag it and our robot re-checks the official source. Reports never change a score.

Is Carbon Forge still online?

Free alerts · no account

Questions about Carbon Forge

How do I connect Carbon Forge?

Use the hosted endpoint https://{instance}.carbonforge.dev/api/mcp in your assistant's MCP settings. The exact settings are in "How to connect" above, as declared in the Official MCP Registry.

Does Carbon Forge need an API key or token?

Yes. The registry entry lists a required value: Authorization. Get it from the publisher.

What tools does Carbon Forge offer?

When Electra Index connected on 24 Oct 2026, it listed 22 tools: pages.list, pages.read, atoms.list, atoms.read, search.global, search.literal, discovery.list_entities, kg.get_related and more. The full list is in "Live check" above.

Is Carbon Forge online?

Yes. Its hosted endpoint answered an MCP connection from Electra Index 2h ago.