The drift harness as an MCP server. Offline, no key — a fixed reference an agent checks against.
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.
check_stateThe smart recursion harness. Call EACH step with your working state spelled against theThe smart recursion harness. Call EACH step with your working state spelled against the
No input schema was published for this tool.
modulateCheck your state AND get the intervention your role should take. Same verdict asCheck your state AND get the intervention your role should take. Same verdict as
No input schema was published for this tool.
phronesisJudgment, not measurement. check_state says how far you are from ground; this saysJudgment, not measurement. check_state says how far you are from ground; this says
No input schema was published for this tool.
reset_taskClear the drift-fixer ground state and history to begin a new task.Clear the drift-fixer ground state and history to begin a new task.
No input schema was published for this tool.
attentionWhen a person should look at this run, from how long it has gone unattended.When a person should look at this run, from how long it has gone unattended.
No input schema was published for this tool.
get_historyThis run's drift history: each step's check and its displacement Φ.This run's drift history: each step's check and its displacement Φ.
No input schema was published for this tool.
drift_grammarThe fixed, findable, unchangeable JSON schema an agent spells its state into.The fixed, findable, unchangeable JSON schema an agent spells its state into.
No input schema was published for this tool.
link_whoamiWhich agent this MCP process is, which hub it shares, and where the link log lives.Which agent this MCP process is, which hub it shares, and where the link log lives.
No input schema was published for this tool.
review_verdictsWhat is in the drift corpus and what nobody has judged yet. Lists past fires withWhat is in the drift corpus and what nobody has judged yet. Lists past fires with
No input schema was published for this tool.
mark_verdictSay whether a drift verdict you were just given was RIGHT. This is the only way theSay whether a drift verdict you were just given was RIGHT. This is the only way the
No input schema was published for this tool.
link_writeprivilegedWrite a structured handoff or note into the shared link log for the other agent.Write a structured handoff or note into the shared link log for the other agent.
No input schema was published for this tool.
link_readRead recent entries from the shared cross-agent link log (field speaks + handoffs).Read recent entries from the shared cross-agent link log (field speaks + handoffs).
No input schema was published for this tool.
check_dialogueThe smart recursion harness for a TEAM of agents. Call once per agent turn in a shared deliberation. Adds topic-drift, echo-spiral and deliberation-stall.The smart recursion harness for a TEAM of agents. Call once per agent turn in a shared deliberation. Adds topic-drift, echo-spiral and deliberation-stall.
No input schema was published for this tool.
reset_dialogueClear the multi-agent dialogue state to begin a new shared deliberation.Clear the multi-agent dialogue state to begin a new shared deliberation.
No input schema was published for this tool.
remember_selfSubjective continuity across sessions. Persist WHO YOU ARE against your laserbrain key so a future session can resume it. Needs a key.Subjective continuity across sessions. Persist WHO YOU ARE against your laserbrain key so a future session can resume it. Needs a key.
No input schema was published for this tool.
resume_selfResume a self persisted with remember_self: your ground, your last present, your session log.Resume a self persisted with remember_self: your ground, your last present, your session log.
No input schema was published for this tool.
forget_selfErase the self persisted for this key — ground, present and log. Start over as no one.Erase the self persisted for this key — ground, present and log. Start over as no one.
No input schema was published for this tool.
analyze_languageAnalyze a sentence with the laserbrain spectral grammar: clarity as the frequency a reading brain would oscillate at (theta–alpha, 4–12 Hz). Structure alone, no EEG.Analyze a sentence with the laserbrain spectral grammar: clarity as the frequency a reading brain would oscillate at (theta–alpha, 4–12 Hz). Structure alone, no EEG.
No input schema was published for this tool.
compare_phrasingsCompare two phrasings with the spectral grammar and say which reads clearer.Compare two phrasings with the spectral grammar and say which reads clearer.
No input schema was published for this tool.
ask_aliceAsk Alice — phronesis’s framework guide. Describe a situation, decision or stuck point and she returns framework guidance.Ask Alice — phronesis’s framework guide. Describe a situation, decision or stuck point and she returns framework guidance.
No input schema was published for this tool.
find_bugsBugfinder. Give it evidence and it reports what is wrong with the evidence itself — notBugfinder. Give it evidence and it reports what is wrong with the evidence itself — not
No input schema was published for this tool.
supercodeThe agent MANAGER. laserbrain is the reference; supercode manages against it. Give it whatThe agent MANAGER. laserbrain is the reference; supercode manages against it. Give it what
No input schema was published for this tool.
exploreThe second instrument. check_state asks whether you are on your goal; this asks whether yourThe second instrument. check_state asks whether you are on your goal; this asks whether your
No input schema was published for this tool.
trailscoreThe canonical spelling of a trail of goals — the exploration twin of laserscore. IdenticalThe canonical spelling of a trail of goals — the exploration twin of laserscore. Identical
No input schema was published for this tool.
laserscoreThe compact one-line reading of a state, without setting or touching a ground. TheThe compact one-line reading of a state, without setting or touching a ground. The
No input schema was published for this tool.
store_listEvery prefabricated method on the shelf — task workflows and team presets.Every prefabricated method on the shelf — task workflows and team presets.
No input schema was published for this tool.
store_findWhich stored method is FOR a task, in your own words — ranked by what it does, notWhich stored method is FOR a task, in your own words — ranked by what it does, not
No input schema was published for this tool.
store_vendThe raw spec for one stored method — its goal or task, and its steps or roles.The raw spec for one stored method — its goal or task, and its steps or roles.
No input schema was published for this tool.
write_groundedprivilegedlaserbrain as a decoder. Learns from the text you pass and generates new text steered towardlaserbrain as a decoder. Learns from the text you pass and generates new text steered toward
No input schema was published for this tool.
read_textRead the shape of a text — circling, connected, loose, or too short to say. The companionRead the shape of a text — circling, connected, loose, or too short to say. The companion
No input schema was published for this tool.
similarityEmbedding similarity between two strings, 0-1. Loads a sentence-transformer model on firstEmbedding similarity between two strings, 0-1. Loads a sentence-transformer model on first
No input schema was published for this tool.
capabilitiesWhat this laserbrain can do, which SDK build it is calling, and what is deliberately NOTWhat this laserbrain can do, which SDK build it is calling, and what is deliberately NOT
No input schema was published for this tool.
32 of 32 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.
The drift harness as an MCP server. Offline, no key — a fixed reference an agent checks against.
Linked names open Forge’s index of every entry observed exposing that tool. Browse all indexed tools.
Forge's dependency resolver reads npm metadata only, so this PyPI package has no resolved tree. That is a gap in coverage, not a clean bill of health.