Compile documents into a persistent, cited knowledge wiki for AI agents. CLI, MCP server, and TypeScript SDK.
Inferred from the transports this listing declares (stdio). A client not listed here hasn’t been ruled out — it just isn’t something Forge can confirm.
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.
ingest_sourceAdd a user-requested document to this knowledge base: fetch a trusted URL or copy a trusted local file into sources/. Writes project files. Returns the saved filename, character count, and whether content was truncated to fit the size limit.Add a user-requested document to this knowledge base: fetch a trusted URL or copy a trusted local file into sources/. Writes project files. Returns the saved filename, character count, and whether content was truncated to fit the size limit.
No input schema was published for this tool.
compile_wikiUpdate the persistent knowledge wiki after source documents change. Writes wiki pages or review candidates according to project policy. Extract concepts from new/changed sources, generate wiki pages, resolve interlinks, and rebuild the index. Requires an LLM provider with credentials.Update the persistent knowledge wiki after source documents change. Writes wiki pages or review candidates according to project policy. Extract concepts from new/changed sources, generate wiki pages, resolve interlinks, and rebuild the index. Requires an LLM provider with credentials.
No input schema was published for this tool.
query_wikiGet a model-generated answer grounded in this knowledge base. For source evidence to reason over yourself, use get_context_pack instead. Selects relevant pages, loads them, and returns a grounded answer with citations. Set save=true to request publication as a wiki page; citation or profile refusal…Get a model-generated answer grounded in this knowledge base. For source evidence to reason over yourself, use get_context_pack instead. Selects relevant pages, loads them, and returns a grounded answer with citations. Set save=true to request publication as a wiki page; citation or profile refusal…
No input schema was published for this tool.
search_pagesSelect pages relevant to a question and return their full content. Uses semantic embeddings when available, falling back to LLM-based selection over the wiki index. Requires an LLM provider.Select pages relevant to a question and return their full content. Uses semantic embeddings when available, falling back to LLM-based selection over the wiki index. Requires an LLM provider.
No input schema was published for this tool.
read_pageRead a single wiki page by slug. Searches concepts/ first, then queries/. Returns the parsed frontmatter and body. No LLM call required.Read a single wiki page by slug. Searches concepts/ first, then queries/. Returns the parsed frontmatter and body. No LLM call required.
No input schema was published for this tool.
lint_wikiRun rule-based quality checks (broken wikilinks, orphans, duplicates, empty pages, broken citations). Returns structured diagnostics. No LLM call.Run rule-based quality checks (broken wikilinks, orphans, duplicates, empty pages, broken citations). Returns structured diagnostics. No LLM call.
No input schema was published for this tool.
wiki_statusNo description publishedThis tool published no description. Forge does not invent one.
get_context_packNo description publishedThis tool published no description. Forge does not invent one.
run_evalprivilegedRun the wiki quality eval harness. fast suite checks health and citation coverage without LLM calls. full suite also LLM-judges a sample of citations (requires an LLM provider). Set record: true to append results to eval history (default false — read-only).Run the wiki quality eval harness. fast suite checks health and citation coverage without LLM calls. full suite also LLM-judges a sample of citations (requires an LLM provider). Set record: true to append results to eval history (default false — read-only).
No input schema was published for this tool.
verify_artifactVerify a hash-pinned artifact ref against the active profile's declared artifact types. Returns manifest metadata (artifactType, slug, sha256, bytes, contentKind, writtenAt) plus a health verdict — NEVER the artifact body. Read-only; no write or store-wide list tool is exposed over MCP.Verify a hash-pinned artifact ref against the active profile's declared artifact types. Returns manifest metadata (artifactType, slug, sha256, bytes, contentKind, writtenAt) plus a health verdict — NEVER the artifact body. Read-only; no write or store-wide list tool is exposed over MCP.
No input schema was published for this tool.
export_okfExport the wiki as an Open Knowledge Format (OKF) v0.1 bundle. `out` defaults to dist/exports/okf and must stay inside the project.Export the wiki as an Open Knowledge Format (OKF) v0.1 bundle. `out` defaults to dist/exports/okf and must stay inside the project.
No input schema was published for this tool.
import_okfImport an OKF bundle from a path INSIDE the project as review candidates. Always staging-only — imported knowledge requires human review/approval before it enters the wiki. Use dryRun to preview.Import an OKF bundle from a path INSIDE the project as review candidates. Always staging-only — imported knowledge requires human review/approval before it enters the wiki. Use dryRun to preview.
No input schema was published for this tool.
list_workflow_actionsList the workflow actions declared by the active profile (id, label, workflow, operation). Read-only; takes no lock and mutates nothing.List the workflow actions declared by the active profile (id, label, workflow, operation). Read-only; takes no lock and mutates nothing.
No input schema was published for this tool.
describe_workflow_actionDescribe one declared workflow action, including its EFFECTIVE permission per surface = min(profile request, local grant, surface cap). The `mcp` surface is hard-capped at staged-write. Read-only.Describe one declared workflow action, including its EFFECTIVE permission per surface = min(profile request, local grant, surface cap). The `mcp` surface is hard-capped at staged-write. Read-only.
No input schema was published for this tool.
run_workflow_actionExecute a declared workflow action. MCP actions are HARD-CAPPED at staged-write: they CANNOT perform trusted writes or satisfy human gates, regardless of what a profile or local config requests. A denied, unknown, or invalid action returns a clean error result rather than crashing.Execute a declared workflow action. MCP actions are HARD-CAPPED at staged-write: they CANNOT perform trusted writes or satisfy human gates, regardless of what a profile or local config requests. A denied, unknown, or invalid action returns a clean error result rather than crashing.
No input schema was published for this tool.
workflow_run_statusReport the status of one workflow run (by runId) or of all runs, classified against the active profile (current / historical / needs-adaptation / blocked-by-config). Read-only and fail-visible: an unavailable store surfaces a problem row, never an empty result. Takes no lock and mutates nothing.Report the status of one workflow run (by runId) or of all runs, classified against the active profile (current / historical / needs-adaptation / blocked-by-config). Read-only and fail-visible: an unavailable store surfaces a problem row, never an empty result. Takes no lock and mutates nothing.
No input schema was published for this tool.
14 of 16 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.
Compile documents into a persistent, cited knowledge wiki for AI agents. CLI, MCP server, and TypeScript SDK.
Linked names open Forge’s index of every entry observed exposing that tool. Browse all indexed tools.
The crawl stopped at the 60-package limit. The rest of the tree was never resolved.
36 more resolved packages are not drawn here (display cap: 24). Every dependency carrying an advisory is drawn regardless of the cap. Full inventory (CycloneDX SBOM)
69 declared dependencies never landed in the tree. They are missing from Forge's resolution, not from the package.
+57 more not listed. The counts by reason above cover all of them.
Not followed: peerDependencies, optionalDependencies. This tree covers runtime dependencies only, so anything those pull in was never resolved.