SEIF
Reference

MCP tools

The Model Context Protocol tool catalog exposed by `seif mcp serve`.

Generated page. Do not edit by hand — built from the SEIF MCP catalog by scripts/sync-docs.mjs and refreshed when main is updated.

The MCP server is this binary — no separate npm package. Tools are registered in internal/mcp/server.go and listed below from the live BuildServer + ListTools surface.

Client config example

{
  "mcpServers": {
    "seif": {
      "command": "seif",
      "args": ["mcp", "serve"],
      "env": {
        "SEIF_ENGINE_TOKEN": "<workspace-key>"
      }
    }
  }
}

Setup guide: ../guides/mcp-setup.md.

Cold start (all MCP hosts)

On initialize, the Go product server (seif mcp serve) returns server instructions with the full resonant grounding kernel and playbook (parity with Python dev-tool instructions=). MCP cannot auto-invoke tools at connect; passive surfaces supplement the contract:

SurfaceIdentifierRole
Initializeinstructions in InitializeResultPlaybook + full grounding.Block()
Resourceseif://grounding/kernelRead kernel without calling a tool
Promptseif_session_startUI cold-start prompt (kernel + derivation reminder)
Toolsession_orientMandatory first tool — grounding + store + memory (canonical)

First assistant message: re-derive H(0), ζ, stance/resonance, f_peak/f_n, (3,6,9); φ coincidence not cause. Other tools are prefixed with “Requires session_orient + derivation paragraph first this session.”

Local (free — no engine token)

ToolMaps toDescription
artifact_read—Run session_orient first this session for grounding + store + memory. Read a workspace .seif artifact (SEIF-ENVELOPE-v1). Returns the parsed frontmatter and JSON body.
artifact_validate—Run session_orient first this session for grounding + store + memory. Validate a .seif file structure and integrity (local, no network).
classification_checkseif classifyRun session_orient first this session for grounding + store + memory. Classify text sensitivity as PUBLIC, INTERNAL, or CONFIDENTIAL using the SEIF auto-classifier (local, no network).
context_queryseif context queryRun session_orient first this session for grounding + store + memory. USE WHEN you need to find relevant code/docs WITHOUT reading whole files (refs first) — lexical pre-filter over structural chunks, returns unresolved ChunkRefs JSON (local, read-only).
howseif howRun session_orient first this session for grounding + store + memory. USE WHEN you need to find the right SEIF CLI verb for a natural-language intent — ranked verb-docs from the shipped capability catalog (parity with seif how). Free, local, lexical-only.
memory_queryseif memory queryRun session_orient first this session for grounding + store + memory. USE WHEN you need to RECALL a past decision, 'where did we decide X', or project history — ranked memory + knowledge hits (parity with seif memory query). Optional semantic blend via local Ollama; uses embedding cache when present.
ollama_chat—Run session_orient first this session for grounding + store + memory. Chat with local Ollama (free, no engine). Uses the SEIF regex should_rag_query (Wave A) to decide whether RAG context would be relevant; reports the decision + the live semantic index freshness (.seif/.cache/memory-embeddings/, rebuilt via seif memory reindex) so the caller can introspect. Wave D MVP: stateless (no thread persistence); RAG decision-surface only (does not retrieve context — that lands in a future wave).
provenance_signseif signRun session_orient first this session for grounding + store + memory. Sign text with the local Ed25519 signing key, returning a SEIF evidence frame (local provenance, no network). Requires seif key generate first.
provenance_verifyseif verifyRun session_orient first this session for grounding + store + memory. Verify a SEIF evidence frame (JSON): recompute the canonical hash, check the Ed25519 signature, re-derive the evidence id (local, no network).
relay_assignmentsseif relay assignmentsRun session_orient first this session for grounding + store + memory. USE WHEN you need to see who is assigned to what in the relay — lists ACTIVE handoff assignments (executor_id + watch_slugs). Local, metadata-only.
relay_claimseif relay claimRun session_orient first this session for grounding + store + memory. USE WHEN you need to take ownership of a relay slug as an executor — claims ACTIVE ownership for an executor_id. Refuses on visible conflict unless also_watch.
relay_closeseif relay closeRun session_orient first this session for grounding + store + memory. USE WHEN you need to terminally finish a relay assignment or sweep stale claims — Mirror of seif relay close.
relay_nextseif relay nextRun session_orient first this session for grounding + store + memory. USE WHEN you need to pick up the next QUEUED task as an executor — atomically claims the oldest queued brief (executor_id: auto). Mirror of seif relay next; use when session_orient.relay.next_in_queue is set.
relay_pollseif relay pollRun session_orient first this session for grounding + store + memory. USE WHEN you need to TRACK a peer agent's progress or see what's queued/done in the relay (the answer to 'I can't see their TTY') — single-shot filtered poll; returns metadata events + next_token (mtime-based).
relay_releaseseif relay releaseRun session_orient first this session for grounding + store + memory. USE WHEN you need to hand a claimed task back to the queue — releases an ACTIVE relay claim back to dispatch. Mirror of seif relay release.

Requires signing key for provenance_sign.

Engine-gated (workspace token required)

ToolMaps toDescription
context_bootstrapconstitutional core (SEIF.md + RESONANCE.json) — after session_orientRun session_orient first this session for grounding + store + memory. Deep constitutional core (SEIF.md, RESONANCE.json) — use AFTER session_orient.
context_retrieveseif context retrieveRun session_orient first this session for grounding + store + memory. USE WHEN you need the actual code/doc SLICES (after context_query refs) instead of loading whole files — orchestrator retrieval loop (local chunk-refs → engine resolved slices). Prefer refs first; slices as needed. Fail-soft when engine unreachable.
get_hygiene_statusstore-v2 hygiene statusRun session_orient first this session for grounding + store + memory. Return the STORE-v2 hygiene status (pending counts, last local check, synced snapshot) — projected from the workspace summary. Requires a workspace key.
get_members_statusmembers snapshot statusRun session_orient first this session for grounding + store + memory. Return the members snapshot status (git pins, owner trio, canonical_writer) — projected from the workspace summary. Requires a workspace key.
get_podseif pod showRun session_orient first this session for grounding + store + memory. Get a single compose pod by its namespace id (user-slug/pod-slug), with images + members. Calls the SEIF engine — requires a workspace key.
get_workspace_summaryengine workspace summaryRun session_orient first this session for grounding + store + memory. Fetch the enriched workspace summary (store_v2 hygiene, members_local, sync_local, ratified config) from the SEIF engine. Requires a workspace key.
grounding_ackderivation self-check heuristicsOptional self-check on your first-paragraph derivation (non-blocking heuristics). Call after session_orient.
list_podsseif pod listRun session_orient first this session for grounding + store + memory. List the compose pods visible to the workspace key (with their images). Calls the SEIF engine — requires a workspace key.
log_appendtransparency log appendRun session_orient first this session for grounding + store + memory. Submit an attestation to the SEIF transparency log, returning entry id + sequence. Requires a workspace key.
log_gettransparency log readRun session_orient first this session for grounding + store + memory. Fetch a seif-log entry by id and INDEPENDENTLY verify its RFC-6962 inclusion proof + signed tree head. Requires a workspace key.
memory_surfaceseif memory-surface / MEMORY.md indexRun session_orient first this session for grounding + store + memory. USE WHEN you need the cross-AI memory bootstrap summary (what's known across sessions) — parity with session-start. Prefer session_orient at session start.
quality_gateseif quality-gateRun session_orient first this session for grounding + store + memory. Score text quality/stance via the SEIF engine (GROUNDED vs DRIFT, grade A–F). Calls the engine API — requires a workspace key.
seif_invokeseif gov … (governance actions)Run session_orient first this session for grounding + store + memory. Invoke a SEIF governance action with structured params. USE WHEN you need to: REMEMBER a durable fact (memory_add) · DEFER work for the next cycle (pending_register) · open/close a unit of work (cycle_start/close_ritual) · APPEND an amendment with no re-sign (amend) · hand off / pick up relay work (relay_brief/relay_handback/relay_next). Full action list in the action param.
session_orientsession orient (grounding + store + memory)Recommended first SEIF tool each session. Returns plain-conduct grounding (calibrate, verify, settle, minimal intervention, human gate) plus store snapshot and memory_surface. No derivation ritual required (pending-2026-06-08-resonance-decouple-value-from-math).
submit_local_snapshotseif … --push-snapshotRun session_orient first this session for grounding + store + memory. Submit a local CLI snapshot (hygiene/members/sync/config) to the engine — same as seif … --push-snapshot. Requires a workspace key.
syncseif pushRun session_orient first this session for grounding + store + memory. Push the local .seif/ workspace state to the engine mirror + transparency log, returning the verify URL + log entry id. Requires a workspace key.
watermark_embedseif watermark embedRun session_orient first this session for grounding + store + memory. Sign a watermark-embed provenance envelope for an (input, output) audio file pair via the SEIF engine. Requires a workspace key.
watermark_extractseif watermark extractRun session_orient first this session for grounding + store + memory. Look up the signed watermark envelope for a recovered audio file via the SEIF engine. Requires a workspace key.

Pass token via client env SEIF_ENGINE_TOKEN or MCP serve flags --token / --token-file.

CLI reference

Complete command and flag reference for the SEIF CLI, generated from the binary's command tree.

HTTP API

The SEIF engine REST surface, generated from its OpenAPI specification.

On this page

Client config exampleCold start (all MCP hosts)Local (free — no engine token)Engine-gated (workspace token required)