Long-term memory for AI coding agents. Facts recorded once, recalled by every client.
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.
BRAINFEATHER_API_KEYAPI keyrequiredYour Brainfeather API key, from https://brainfeather.com/api-keys
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.
get_contextCall this FIRST, before writing code or answering anything about this project.Call this FIRST, before writing code or answering anything about this project.
No input schema was published for this tool.
search_memoryLook up what the user has already decided about a specific topic. Call beforeLook up what the user has already decided about a specific topic. Call before
No input schema was published for this tool.
list_entitiesList tools, languages and concepts connected to memories in the current project.List tools, languages and concepts connected to memories in the current project.
No input schema was published for this tool.
traverse_graphShow project-scoped memories and entities connected to one entity. Use when aShow project-scoped memories and entities connected to one entity. Use when a
No input schema was published for this tool.
save_memoryRecord one durable fact explicitly stated or confirmed by the user. Call when aRecord one durable fact explicitly stated or confirmed by the user. Call when a
No input schema was published for this tool.
capture_activityQueue durable facts inferred from agent activity for the user's review.Queue durable facts inferred from agent activity for the user's review.
No input schema was published for this tool.
onboard_projectImport durable facts the user already wrote in AGENTS.md, CLAUDE.md, .cursorrules,Import durable facts the user already wrote in AGENTS.md, CLAUDE.md, .cursorrules,
No input schema was published for this tool.
forget_memoryPermanently delete a memory only when the user says it was recorded in error.Permanently delete a memory only when the user says it was recorded in error.
No input schema was published for this tool.
8 of 8 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.
Long-term memory for AI coding agents. Facts recorded once, recalled by every client.
Linked names open Forge’s index of every entry observed exposing that tool. Browse all indexed tools.
The crawl stopped at the depth-4 limit. Anything below that level was never resolved.
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)
54 declared dependencies never landed in the tree. They are missing from Forge's resolution, not from the package.
+42 more not listed. The counts by reason above cover all of them.
Not followed: peerDependencies. This tree covers runtime dependencies only, so anything those pull in was never resolved.