Cloud or self-hosted knowledge for AI agents: hybrid search, reranking, GraphRAG, scoped MCP tools.
Inferred from the transports this listing declares (stdio, streamable-http). A client not listed here hasn’t been ruled out — it just isn’t something Forge can confirm.
HIAI_DOCS_API_KEYAPI keyrequiredCreate an API key in your self-hosted DocsMint browser UI. The stdio bridge uses it only with your own API; it does not install the Cloud OAuth server. Prefer workspace-bound or category-scoped…
Declared by the author in the official MCP registry. Forge does not store, broker, or ever see these values — the config below is scaffolded with placeholders you fill in locally.
Verification confirms publisher identity (repo ownership), not code safety. The security scan covers known CVEs and suspicious install scripts.
Read out of the source npm actually ships, at scan time. The package was never executed. Tools registered dynamically at runtime, or hidden inside bundled or minified code, can be missed — so this is a floor on the tool surface, not a complete census of it.
list_categoriesList categories visible to the API key. Category keys receive only their bound category.List categories visible to the API key. Category keys receive only their bound category.
No input schema was published for this tool.
create_categoryCreate a category. Requires a workspace key with write access; category keys cannot mutate categories.Create a category. Requires a workspace key with write access; category keys cannot mutate categories.
No input schema was published for this tool.
list_tagsList tags visible in the workspace or bound category.List tags visible in the workspace or bound category.
No input schema was published for this tool.
get_related_documentsTraverse the knowledge graph from one authorized document.Traverse the knowledge graph from one authorized document.
No input schema was published for this tool.
search_knowledge_graphSearch connected knowledge using authorized seed documents. Category keys may use only documents in their category.Search connected knowledge using authorized seed documents. Category keys may use only documents in their category.
No input schema was published for this tool.
get_document_index_statusRead the current indexing and knowledge-pipeline status of a document.Read the current indexing and knowledge-pipeline status of a document.
No input schema was published for this tool.
refresh_document_indexRequest reindexing after a document or metadata change. Requires write access.Request reindexing after a document or metadata change. Requires write access.
No input schema was published for this tool.
create_documentCreate a new document. Optionally provide initial markdown content and a folder ID.Create a new document. Optionally provide initial markdown content and a folder ID.
No input schema was published for this tool.
create_folderCreate a new folder, optionally nested under a parent folder.Create a new folder, optionally nested under a parent folder.
No input schema was published for this tool.
create_snapshotCreate a named snapshot (labelled version) of a document from its current content.Create a named snapshot (labelled version) of a document from its current content.
No input schema was published for this tool.
export_documentExport a document as markdown. Returns the rendered markdown content.Export a document as markdown. Returns the rendered markdown content.
No input schema was published for this tool.
get_documentFetch a single document by ID. Returns full content, metadata, and tags.Fetch a single document by ID. Returns full content, metadata, and tags.
No input schema was published for this tool.
list_documentsList documents with pagination, optionally filtered by folder or tag.List documents with pagination, optionally filtered by folder or tag.
No input schema was published for this tool.
list_foldersList folders, optionally scoped to a parent folder. Returns a flat list of immediate children.List folders, optionally scoped to a parent folder. Returns a flat list of immediate children.
No input schema was published for this tool.
search_documentsHybrid search across documents (full-text + semantic). Supports filtering by folder and tags.Hybrid search across documents (full-text + semantic). Supports filtering by folder and tags.
No input schema was published for this tool.
update_documentUpdate an existing document's title and/or content. The server creates a new version on each update.Update an existing document's title and/or content. The server creates a new version on each update.
No input schema was published for this tool.
get_version_historyList the version history for a document. Optionally restrict to named snapshots.List the version history for a document. Optionally restrict to named snapshots.
No input schema was published for this tool.
17 of 17 tools published a description.
Tool names and descriptions are written by the publisher and shown verbatim as inert text. They are the strings an MCP client passes to a model, so Forge scans them for prompt-injection patterns — any finding appears with the security scan above. “Privileged” is a keyword match on the tool name, not an audit of what the tool does: a benign-sounding name can still do anything.
Cloud or self-hosted knowledge for AI agents: hybrid search, reranking, GraphRAG, scoped MCP tools.
Linked names open Forge’s index of every entry observed exposing that tool. Browse all indexed tools.
Not followed: peerDependencies, optionalDependencies. This tree covers runtime dependencies only, so anything those pull in was never resolved.