The official Svelte MCP server providing docs and autofixing tools for Svelte development
Nothing to run from here
Carbon Forge is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
96/100
tool-list score
22
tools declared
remote
at its publisher
—
calls last 7d
What it does
One record of code, files and pages that people and agents read and write, with lanes and git.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http carbon-forge-mcp https://carbonforge.dev/api/mcp
# 2 — ask your agent for something these tools do
# pages.list, pages.read, atoms.list and 19 more
Carbon Forge costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
1AAll 1 server
100monkeys-ai1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
Claude Codedeclared by this listing
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it.
claude mcp add --scope user --transport http carbon-forge-mcp https://carbonforge.dev/api/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it answers at its publisher’s own address: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it asks of you
Nothing is required, but it can take Authorization header (Optional. Bearer <token> from settings, API tokens. Without it the endpoint serves public workspaces read-only; a token is needed to write or read private content.) if you want to set it.
What it writes
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
What you approve
22 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
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
| Parameter | Type | Required | Notes |
|---|---|---|---|
| limit | integer | no | — |
| cursor | string | no | — |
| path_prefix | string | no | — |
| body_contains | string | no | — |
| sort | string | no | Order the listing by path (the default), last update, or creation time. |
| direction | string | no | Direction for sort. Ascending by default. |
| metadata | object | no | Keep only entries whose metadata contains every one of these keys with an equal value; a second key narrows the result. Values are strings, numbers or booleans, and the match is against top-level keys |
| include_metadata | boolean | no | Carry each entry's metadata object in the response. Off by default, because a metadata bag can be large and a listing is a scan surface. |
| workspace | string | no | Workspace (slug or UUID) this call acts in. Overrides the per-token current-workspace pointer for this call only — read-only, it never moves the pointer. Omit to use the pointer set by `me.set_current |
| instance | string | no | Instance (slug or UUID) to resolve a workspace slug within. Only meaningful for apex tokens, which have no home instance; instance-locked tokens always resolve within their own. |
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
| Parameter | Type | Required | Notes |
|---|---|---|---|
| pathOrId | string | yes | Either the path of the page/atom (e.g. "guides/foo" — no leading slash, lowercase, slash-separated) or the UUID. Paths and UUIDs both resolve inside the workspace this call resolved to: the `workspace |
| section | string | no | A heading's plain text (case-insensitive, whitespace-trimmed). When given, the body returned is that heading and every block down to the next heading at the same or shallower level, instead of the who |
| lane | string | no | A lane's label. On a write, the patch is stored on the lane, validated against the lane's view, and the trunk is not written. On a read, the body is the trunk's current body with the lane's patches ap |
| workspace | string | no | Workspace (slug or UUID) this call acts in. Overrides the per-token current-workspace pointer for this call only — read-only, it never moves the pointer. Omit to use the pointer set by `me.set_current |
| instance | string | no | Instance (slug or UUID) to resolve a workspace slug within. Only meaningful for apex tokens, which have no home instance; instance-locked tokens always resolve within their own. |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| limit | integer | no | — |
| cursor | string | no | — |
| path_prefix | string | no | — |
| body_contains | string | no | — |
| sort | string | no | Order the listing by path (the default), last update, or creation time. |
| direction | string | no | Direction for sort. Ascending by default. |
| metadata | object | no | Keep only entries whose metadata contains every one of these keys with an equal value; a second key narrows the result. Values are strings, numbers or booleans, and the match is against top-level keys |
| include_metadata | boolean | no | Carry each entry's metadata object in the response. Off by default, because a metadata bag can be large and a listing is a scan surface. |
| workspace | string | no | Workspace (slug or UUID) this call acts in. Overrides the per-token current-workspace pointer for this call only — read-only, it never moves the pointer. Omit to use the pointer set by `me.set_current |
| instance | string | no | Instance (slug or UUID) to resolve a workspace slug within. Only meaningful for apex tokens, which have no home instance; instance-locked tokens always resolve within their own. |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| pathOrId | string | yes | Either the path of the page/atom (e.g. "guides/foo" — no leading slash, lowercase, slash-separated) or the UUID. Paths and UUIDs both resolve inside the workspace this call resolved to: the `workspace |
| section | string | no | A heading's plain text (case-insensitive, whitespace-trimmed). When given, the body returned is that heading and every block down to the next heading at the same or shallower level, instead of the who |
| lane | string | no | A lane's label. On a write, the patch is stored on the lane, validated against the lane's view, and the trunk is not written. On a read, the body is the trunk's current body with the lane's patches ap |
| workspace | string | no | Workspace (slug or UUID) this call acts in. Overrides the per-token current-workspace pointer for this call only — read-only, it never moves the pointer. Omit to use the pointer set by `me.set_current |
| instance | string | no | Instance (slug or UUID) to resolve a workspace slug within. Only meaningful for apex tokens, which have no home instance; instance-locked tokens always resolve within their own. |
Hybrid FTS + pgvector + RRF search. Returns Markdown excerpts.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| q | string | yes | — |
| scope | string | no | — |
| limit | integer | no | — |
| cursor | string | no | — |
| perspective | string | no | Only this workspace's pages and atoms the perspective holds (perspectives.list), at paths with its root stripped. |
| workspace | string | no | Workspace (slug or UUID) this call acts in. Overrides the per-token current-workspace pointer for this call only — read-only, it never moves the pointer. Omit to use the pointer set by `me.set_current |
| instance | string | no | Instance (slug or UUID) to resolve a workspace slug within. Only meaningful for apex tokens, which have no home instance; instance-locked tokens always resolve within their own. |
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
| Parameter | Type | Required | Notes |
|---|---|---|---|
| q | string | yes | — |
| scope | string | no | — |
| kinds | array | no | — |
| context_lines | integer | no | — |
| case_sensitive | boolean | no | — |
| limit | integer | no | — |
| cursor | string | no | — |
| workspace | string | no | Workspace (slug or UUID) this call acts in. Overrides the per-token current-workspace pointer for this call only — read-only, it never moves the pointer. Omit to use the pointer set by `me.set_current |
| instance | string | no | Instance (slug or UUID) to resolve a workspace slug within. Only meaningful for apex tokens, which have no home instance; instance-locked tokens always resolve within their own. |
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
| Parameter | Type | Required | Notes |
|---|---|---|---|
| workspace_id | string | no | — |
| workspace_slug | string | no | — |
| kind | string | yes | — |
| sort | string | no | — |
| q | string | no | — |
| filters | object | no | — |
| cursor | string | no | — |
| limit | integer | no | — |
| workspace | string | no | Workspace (slug or UUID) this call acts in. Overrides the per-token current-workspace pointer for this call only — read-only, it never moves the pointer. Omit to use the pointer set by `me.set_current |
| instance | string | no | Instance (slug or UUID) to resolve a workspace slug within. Only meaningful for apex tokens, which have no home instance; instance-locked tokens always resolve within their own. |
Semantic nearest-neighbors via similarity_edges.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| pathOrId | string | yes | Either the path of the page/atom (e.g. "guides/foo" — no leading slash, lowercase, slash-separated) or the UUID. Paths and UUIDs both resolve inside the workspace this call resolved to: the `workspace |
| kind | string | yes | — |
| limit | integer | no | — |
| workspace | string | no | Workspace (slug or UUID) this call acts in. Overrides the per-token current-workspace pointer for this call only — read-only, it never moves the pointer. Omit to use the pointer set by `me.set_current |
| instance | string | no | Instance (slug or UUID) to resolve a workspace slug within. Only meaningful for apex tokens, which have no home instance; instance-locked tokens always resolve within their own. |
List incoming + outgoing cross-links for a page or atom.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| pathOrId | string | yes | Either the path of the page/atom (e.g. "guides/foo" — no leading slash, lowercase, slash-separated) or the UUID. Paths and UUIDs both resolve inside the workspace this call resolved to: the `workspace |
| kind | string | yes | — |
| workspace | string | no | Workspace (slug or UUID) this call acts in. Overrides the per-token current-workspace pointer for this call only — read-only, it never moves the pointer. Omit to use the pointer set by `me.set_current |
| instance | string | no | Instance (slug or UUID) to resolve a workspace slug within. Only meaningful for apex tokens, which have no home instance; instance-locked tokens always resolve within their own. |
List revisions for a page or atom (cursor-paginated).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| kind | string | yes | — |
| pathOrId | string | yes | Either the path of the page/atom (e.g. "guides/foo" — no leading slash, lowercase, slash-separated) or the UUID. Paths and UUIDs both resolve inside the workspace this call resolved to: the `workspace |
| limit | integer | no | — |
| cursor | string | no | — |
| workspace | string | no | Workspace (slug or UUID) this call acts in. Overrides the per-token current-workspace pointer for this call only — read-only, it never moves the pointer. Omit to use the pointer set by `me.set_current |
| instance | string | no | Instance (slug or UUID) to resolve a workspace slug within. Only meaningful for apex tokens, which have no home instance; instance-locked tokens always resolve within their own. |
Fetch a specific revision (returns Markdown body).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| kind | string | yes | — |
| pathOrId | string | yes | Either the path of the page/atom (e.g. "guides/foo" — no leading slash, lowercase, slash-separated) or the UUID. Paths and UUIDs both resolve inside the workspace this call resolved to: the `workspace |
| revision_id | integer | yes | — |
| workspace | string | no | Workspace (slug or UUID) this call acts in. Overrides the per-token current-workspace pointer for this call only — read-only, it never moves the pointer. Omit to use the pointer set by `me.set_current |
| instance | string | no | Instance (slug or UUID) to resolve a workspace slug within. Only meaningful for apex tokens, which have no home instance; instance-locked tokens always resolve within their own. |
Markdown-level diff between two revisions of the same page or atom. Returns segments (op: equal | insert | delete) plus both Markdown projections.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| kind | string | yes | — |
| pathOrId | string | yes | Either the path of the page/atom (e.g. "guides/foo" — no leading slash, lowercase, slash-separated) or the UUID. Paths and UUIDs both resolve inside the workspace this call resolved to: the `workspace |
| revision_a_id | integer | yes | — |
| revision_b_id | integer | yes | — |
| workspace | string | no | Workspace (slug or UUID) this call acts in. Overrides the per-token current-workspace pointer for this call only — read-only, it never moves the pointer. Omit to use the pointer set by `me.set_current |
| instance | string | no | Instance (slug or UUID) to resolve a workspace slug within. Only meaningful for apex tokens, which have no home instance; instance-locked tokens always resolve within their own. |
Fetch metadata for a single media item.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| media_id | string | yes | — |
| workspace | string | no | Workspace (slug or UUID) this call acts in. Overrides the per-token current-workspace pointer for this call only — read-only, it never moves the pointer. Omit to use the pointer set by `me.set_current |
| instance | string | no | Instance (slug or UUID) to resolve a workspace slug within. Only meaningful for apex tokens, which have no home instance; instance-locked tokens always resolve within their own. |
List the comment thread for a page or atom.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| target_kind | string | yes | — |
| target_pathOrId | string | yes | Either the path of the page/atom (e.g. "guides/foo" — no leading slash, lowercase, slash-separated) or the UUID. Paths and UUIDs both resolve inside the workspace this call resolved to: the `workspace |
| workspace | string | no | Workspace (slug or UUID) this call acts in. Overrides the per-token current-workspace pointer for this call only — read-only, it never moves the pointer. Omit to use the pointer set by `me.set_current |
| instance | string | no | Instance (slug or UUID) to resolve a workspace slug within. Only meaningful for apex tokens, which have no home instance; instance-locked tokens always resolve within their own. |
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
| Parameter | Type | Required | Notes |
|---|---|---|---|
| instance | string | no | — |
| workspace | string | no | — |
| known_grounding_at | string | no | ISO-8601 timestamp of the instance grounding document you already hold; when it equals the stored document exactly, the reply acknowledges it as unchanged instead of resending the body, and any other |
| known_workspace_grounding_at | string | no | ISO-8601 timestamp of the resolved workspace grounding document you already hold; when it equals the stored document exactly, the reply acknowledges it as unchanged instead of resending the body, and |
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.
No parameter schema on file.
Resolve a workspace slug to its id, role, and archived state. 404 when the caller isn't a member (no enumeration).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| slug | string | yes | — |
| instance | string | no | — |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| filter | string | no | — |
| query | string | no | — |
| limit | integer | no | — |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| filter | string | no | — |
| query | string | no | — |
| instance_id | string | no | — |
| limit | integer | no | — |
Search instance and workspace metadata + grounding documents. Returns parallel lists for both scopes.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| q | string | yes | — |
| scope | string | no | — |
| filter | string | no | — |
| limit | integer | no | — |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| path_or_id | string | yes | The tree's path or its UUID. |
| revision_id | integer | no | — |
| snapshot_id | string | no | Read the revision this snapshot names (snapshots.cut); not with revision_id or lane. |
| path_prefix | string | no | — |
| offset | integer | no | — |
| limit | integer | no | — |
| lane | string | no | A lane's label. On a write, the change is stored on the lane — a tree as a manifest delta, a library entry as a blob reference — and the trunk is not written. On a read, the trunk's current state with |
| workspace | string | no | Workspace (slug or UUID) this call acts in. Overrides the per-token current-workspace pointer for this call only — read-only, it never moves the pointer. Omit to use the pointer set by `me.set_current |
| instance | string | no | Instance (slug or UUID) to resolve a workspace slug within. Only meaningful for apex tokens, which have no home instance; instance-locked tokens always resolve within their own. |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| path | string | no | A path in the workspace, e.g. "repos/pilot/bin": case kept, slash-separated, no leading slash. Omit or pass "" for the root. |
| lane | string | no | A lane label. When given, every node carries lane: { patched, conflict } against that lane; a directory is marked when anything below it is. Members only. |
| surface | string | no | Only entities whose metadata's surface is this one (a tree's files go with their tree). |
| perspective | string | no | Only what this perspective holds (perspectives.list), at paths with its root stripped; an anonymous caller sees its public part. Not with surface. |
| offset | integer | no | — |
| limit | integer | no | Nodes per page, default 100. |
| workspace | string | no | Workspace (slug or UUID) this call acts in. Overrides the per-token current-workspace pointer for this call only — read-only, it never moves the pointer. Omit to use the pointer set by `me.set_current |
| instance | string | no | Instance (slug or UUID) to resolve a workspace slug within. Only meaningful for apex tokens, which have no home instance; instance-locked tokens always resolve within their own. |
Free
$0 forever
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Carbon Forge or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATool-list grade · score 96 / 100
Release 1.0.0 · scanned 28 Oct 2026
Graded from the tools this server lists, not from its source code.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score96
Findings0 threat · 0 capability
Capabilityminimal
Coveragemanifest
Verificationnot in this report
Surface digest3799a959c171a9f6a27a564c0abffbfda01509539d4e9c5504fa5ed51fc7f66a
Score vectorthreat 100 → client 96
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | minimal | capability blast radius (minimal) — client exposure if the model is manipulated | −0 |
| coverage-honesty | manifest | inspection depth (manifest) — how much of the target the scan could see | −4 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.
Tool surfaceread
Implementation sourcenot available
Package metadatanot available
Live transportnot available
The implementation source was not read — this reflects the declared tool metadata only.
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. minimal is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| pages.list | no tags | |
| pages.read | no tags | |
| atoms.list | no tags | |
| atoms.read | no tags | |
| search.global | no tags | |
| search.literal | no tags | |
| discovery.list_entities | untrusted-input | untrusted-input: keyword "browse" |
| kg.get_related | no tags | |
| kg.list_cross_links | no tags | |
| revisions.list | no tags | |
| revisions.get | untrusted-input | untrusted-input: keyword "fetch" |
| revisions.compare | no tags | |
| media.read | untrusted-input | untrusted-input: keyword "fetch" |
| comments.list | no tags | |
| cortex.ground | no tags | |
| workspaces.list | no tags | |
| workspaces.resolve_slug | no tags | |
| discovery.list_instances | no tags | |
| discovery.list_workspaces | no tags | |
| discovery.search | no tags | |
| trees.get | no tags | |
| files.list | untrusted-input | untrusted-input: keyword "browse" |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digest3799a959c171a9f6
Scanned2026-10-28
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 1.0.0.
1.0.0
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish Carbon Forge can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.