Evidence-backed codebase understanding with file:line citations, for AI clients over MCP.
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.
rune_rescanRe-scan the project from disk and refresh Rune's understanding graph. Call this after significant code changes if `rune watch` isn't already running in the background.Re-scan the project from disk and refresh Rune's understanding graph. Call this after significant code changes if `rune watch` isn't already running in the background.
No input schema was published for this tool.
rune_get_overviewGet a high-level architecture summary of the software: detected stack, component count, route count. Start here.Get a high-level architecture summary of the software: detected stack, component count, route count. Start here.
No input schema was published for this tool.
rune_list_componentsList all React components Rune has identified, with file location and detection kind (function/class).List all React components Rune has identified, with file location and detection kind (function/class).
No input schema was published for this tool.
rune_list_routesList all API/page routes Rune has identified across Express and Next.js (pages + app router).List all API/page routes Rune has identified across Express and Next.js (pages + app router).
No input schema was published for this tool.
rune_searchSearch facts and derived understanding by name, file path, or route path substring. Use this to find where something lives before reading files directly.Search facts and derived understanding by name, file path, or route path substring. Use this to find where something lives before reading files directly.
No input schema was published for this tool.
rune_explainGiven a fact or derived-conclusion id (as returned by other rune_ tools), return the full evidence trail: the raw fact(s) it's based on, file, line, and matched source text.Given a fact or derived-conclusion id (as returned by other rune_ tools), return the full evidence trail: the raw fact(s) it's based on, file, line, and matched source text.
No input schema was published for this tool.
rune_get_file_dependenciesGet the internal (relative-import) dependency list for a given file path, as recorded in the understanding graph.Get the internal (relative-import) dependency list for a given file path, as recorded in the understanding graph.
No input schema was published for this tool.
rune_get_memoryGet durable project-specific knowledge Rune has recorded: conventions, required commands, known pitfalls. Each entry has a status (proposed/approved/rejected) and confidence score -- only 'approved' entries should be treated as trusted; 'proposed' entries are unverified and should be treated as a h…Get durable project-specific knowledge Rune has recorded: conventions, required commands, known pitfalls. Each entry has a status (proposed/approved/rejected) and confidence score -- only 'approved' entries should be treated as trusted; 'proposed' entries are unverified and should be treated as a h…
No input schema was published for this tool.
rune_get_experienceGet the history of past task attempts recorded for this project: what was tried, whether it succeeded or failed, and why. This is raw history, not verified rules -- use rune_get_memory for trusted, approved conventions.Get the history of past task attempts recorded for this project: what was tried, whether it succeeded or failed, and why. This is raw history, not verified rules -- use rune_get_memory for trusted, approved conventions.
No input schema was published for this tool.
rune_get_security_findingsGet all security findings Rune has detected in this project: exposed secrets, dangerous shell execution, risky CI/CD workflow permissions, and typosquat-shaped dependencies. Use this before merging a PR or reviewing a codebase for security risk -- this is the single call that answers 'are there sec…Get all security findings Rune has detected in this project: exposed secrets, dangerous shell execution, risky CI/CD workflow permissions, and typosquat-shaped dependencies. Use this before merging a PR or reviewing a codebase for security risk -- this is the single call that answers 'are there sec…
No input schema was published for this tool.
rune_verify_factRe-check a single fact (by id, as returned by other rune_ tools) against the current state of its source file, instead of trusting what was recorded at the last `rune scan`. Returns 'confirmed' if the code still matches, 'stale' with both the old and new evidence lines if it changed, or 'file_missi…Re-check a single fact (by id, as returned by other rune_ tools) against the current state of its source file, instead of trusting what was recorded at the last `rune scan`. Returns 'confirmed' if the code still matches, 'stale' with both the old and new evidence lines if it changed, or 'file_missi…
No input schema was published for this tool.
rune_check_driftRe-check every fact in the graph against the live state of the code and summarize how much has drifted since the last `rune scan`. Cheap: re-reads only the specific line each fact points to, not a full re-parse of the project. Use this to decide whether the current graph is still trustworthy before…Re-check every fact in the graph against the live state of the code and summarize how much has drifted since the last `rune scan`. Cheap: re-reads only the specific line each fact points to, not a full re-parse of the project. Use this to decide whether the current graph is still trustworthy before…
No input schema was published for this tool.
rune_agentNo description publishedThis tool published no description. Forge does not invent one.
12 of 13 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.
Evidence-backed codebase understanding with file:line citations, for AI clients over MCP.
Linked names open Forge’s index of every entry observed exposing that tool. Browse all indexed tools.
This entry publishes no npm package, so Forge has no dependency tree for it. That is a gap in coverage — not a statement that it has no dependencies.