MCP Tools Reference

Complete reference for all 100 MCP tools across 21 modules. All tools are prefixed with remb__ when invoked.

Memory Tools

Manage persistent AI memories organized by tier (core, active, archive) and category (preference, pattern, decision, correction, knowledge, general, user_profile, example).

ToolDescriptionRequired Params
memory_listList memories. Filter by tier, category, or project.
memory_searchSemantic search across memories.query
memory_load_contextLoad core + relevant active memories. Pass mode='lean' to get id+title handles only (~70% smaller) then fetch bodies with memory_get.
memory_getFetch full memory bodies by id. Pair with mode='lean' to load just what you need.ids
memory_createCreate a new memory. Use category='example' for canonical worked examples that ground the agent's behaviour.title, content
memory_updateUpdate an existing memory.id
memory_deleteDelete a memory by ID.id
memory_promoteChange tier (archive ↔ active ↔ core).id, tier
memory_statsMemory usage statistics — count, tokens, categories.
memory_image_uploadUpload an image to a memory with OCR.memory_id, image_data, filename, mime_type
memory_image_listList images attached to a memory.memory_id

Conversation Tools

Track what AI discussed and accomplished across sessions. Auto-summarized and embedded for semantic search.

ToolDescriptionRequired Params
conversation_logLog what you discussed or accomplished. Pass domain (coding|research|support|ops|general) so the summariser variant matches your agent.summary
conversation_historyLoad recent conversation history. Pass mode='compact' for a deterministic statistical rollup of older entries + recent_window verbatim — keeps long-running agents under their context budget.
conversation_searchSemantic search across conversation history.query

Project Tools

ToolDescriptionRequired Params
projects_listList all projects with feature/entry counts.
project_getGet project details, features, tech stack, scan info.project_slug
project_createCreate a new project.name, slug
project_init_localCreate a lightweight project with no GitHub repo or scan required — start preserving context immediately.name
project_updateUpdate project name, description, or settings.project_slug
project_deleteDelete project and all data. Permanent.project_slug, confirm

Context Tools

ToolDescriptionRequired Params
context_saveSave a context entry for a feature.project_slug, feature_name, content
context_getRetrieve context entries, optionally filtered by feature.project_slug
context_bundleFull project context as markdown — memories, features, tech stack.project_slug
session_startUnified session start. Full mode returns XML-structured output (<project>, <core_memories>, <examples>, <features>, <recent_activity>, <context_budget>). Pass mode='lean' for a compact handle manifest ~70% smaller. Omit project_slug to auto-detect.

Scan Tools

ToolDescriptionRequired Params
scan_triggerTrigger a cloud scan. Returns scan ID for tracking.project_slug
scan_statusCheck scan progress — percentage, logs, results.scan_id
diff_analyzeAnalyze a git diff and save feature-level changes.project_slug, diff
scan_on_pushToggle auto-scan on push via GitHub webhook.project_slug, enabled

Feature Tools

ToolDescriptionRequired Params
feature_listList all features for a project.project_slug
feature_getGet detailed knowledge for a feature — decisions, gotchas, dependencies.project_slug, feature_name
feature_updateUpdate a feature name or description.feature_id
feature_deleteDelete a feature and its context entries.feature_id

Plan Tools

Multi-phase project plans with IDE integration and status tracking.

ToolDescriptionRequired Params
plan_listList active plans for a project.project_slug
plan_getGet plan details with phases and messages.plan_id
plan_update_phaseUpdate a phase status.phase_id, status
plan_phasesGet active phases as markdown for .remb integration.project_slug
plan_create_phaseAdd a new phase to a plan.plan_id, title
plan_completeMark a plan as completed.plan_id

Graph Tools

Traverse the knowledge graph — entities, relationships, code dependencies.

ToolDescriptionRequired Params
graph_queryMulti-hop traversal from any entity (up to 4 hops).entity_type, entity_id
graph_relatedEverything related to a feature — memories, context, conversations.feature_id or project_slug + feature_name
explore_code_graphBrowse code-level graph — files, functions, classes, imports.project_slug
search_code_symbolsSemantic search across code symbols.query, project_slug

Cross-Project Tools

ToolDescriptionRequired Params
cross_project_searchSearch across ALL projects for features, context, memories.query
cross_project_patternsFind architectural patterns shared across projects.pattern_query

Preview Tools

ToolDescriptionRequired Params
preview_deployDeploy a live preview to Vercel.project_slug
preview_listList previews for a project.
preview_statusCheck deploy status.preview_id
preview_stopStop an active preview.preview_id
preview_deleteDelete a preview record.preview_id

Repo Tools

ToolDescriptionRequired Params
file_readRead a file from the project's GitHub repo.project_slug, path
file_treeBrowse the file tree.project_slug

Audit Tools

ToolDescriptionRequired Params
audit_listList recent AI code audit reports.project_slug
audit_getGet full audit details with findings.audit_id
audit_triggerTrigger an on-demand code audit.project_slug

Action Log Tools

Multi-agent coordination — prevent conflicts when multiple AI agents work on the same project.

ToolDescriptionRequired Params
action_logRecord an action with reasoning.action, intent, reasoning, targets
action_queryCheck what other agents did recently.project_id
action_checkCheck if files had agent actions.project_id, targets
action_claimClaim a scope so others avoid it.project_id, scope, reasoning
action_releaseRelease a claimed scope.project_id, scope

Session Tools

Track events, create checkpoints, and manage file history across AI sessions.

ToolDescriptionRequired Params
track_eventRecord session events — context switches, edits, branch changes.project_slug, event_type
checkpoint_createSnapshot files before bulk edits.project_slug, file_paths
checkpoint_restoreRestore files from a checkpoint.snapshot_group
checkpoint_listList available checkpoints.project_slug
file_historyVersion history of a file across scans.project_slug, file_path
file_restoreGet content of a specific file version.snapshot_id
session_timelineRecent activity timeline.
diff_between_scansCompare files changed between two scans.

Personal Memory Tools

Personal-memory primitives — current focus, blockers, lessons, recurring problems, people — plus proactive helpers that flag decision conflicts and synthesize a weekly brief.

ToolDescriptionRequired Params
focus_setSet the user's current focus (singleton per scope, stored as core memory).content
focus_getGet the current focus for a scope.
blocker_addRecord something the user is blocked on (timestamps the blocker).title
blocker_resolveMark a blocker resolved; optionally promote to a lesson.id
blocker_listList active blockers with days-since-blocked.
lesson_addRecord a lesson learned.title, content
lesson_listList lessons learned, newest first.
recurring_problem_logLog an occurrence; flags pattern_detected on the 3rd hit.problem
person_setAdd or update a person in the user's context (upsert by name).name
person_listList people in the user's context.
decision_checkBefore recommending an action, surface prior decisions that may contradict it.proposed_action
weekly_briefStructured brief: wins, decisions, blockers, recurring patterns, recommendation.

Profile Tools

Cross-project user profile — name, role, communication style, preferred stack, things to never do. Stored as global memories with category='user_profile' so they apply to every project automatically.

ToolDescriptionRequired Params
profile_setAdd or update a profile field (e.g. name, role, stack, never_do).key, value
profile_getRead all profile fields, or one by key.
profile_clearDelete a profile field.key

Skill Tools

Procedural memory — reusable skills the agent can search, load, and self-heal. Store HOW to do something (triggers, exact commands, gotchas, verification steps); auto-suggested at session start when the user's task semantically matches.

ToolDescriptionRequired Params
skill_createSave a reusable procedural skill (markdown body up to 64 KB).name, content
skill_listList the user's skills, optionally scoped to a project.
skill_loadReturn the full markdown content of a single skill.asset_id
skill_suggestSemantic match: given a task description, return top-N skills to consider loading.query
skill_record_outcomeRecord success/failure for a skill; flags skills that need review.asset_id, success
skill_patchSelf-healing: replace an exact substring of a skill's content. Creates a new version.asset_id, old_text, new_text

Scratchpad Tools

File-based context offload. Write large tool outputs (scans, audits, diffs) to a session-scoped scratchpad path so they stay out of the prompt; read on demand. 256 KiB cap per entry, Redis-backed with 24h TTL.

ToolDescriptionRequired Params
scratchpad_writeSave large content to a session-scoped path. Path must be relative; no '..'.session_id, path, content
scratchpad_readRead content previously written.session_id, path
scratchpad_listList all paths in the session scratchpad.session_id
scratchpad_deleteDelete an entry.session_id, path

Briefing Tools

Typed session-handoff payloads. At session end, save a briefing (focus, decisions, blockers, recent files, working-memory keys) so the next session loads it as a markdown prompt block in one tool call instead of replaying the full transcript. Each successful load silently extends the 30-day TTL so active sessions never expire.

ToolDescriptionRequired Params
briefing_saveSave typed briefing for a session.session_id
briefing_loadLoad latest briefing as a rendered markdown block.session_id

Memory Telemetry Tools

Detect context poisoning. Score the downstream outcome of every memory you act on — success, rejection, or undo (weighted strongest). Quarantine candidates surface memories whose negative-outcome score exceeds the threshold.

ToolDescriptionRequired Params
memory_feedbackRecord outcome (success | rejection | undo) for a retrieved memory.memory_id, outcome
memory_quarantine_candidatesList memories whose negative-outcome score ≥ threshold (default 0.7).

Multi-Agent Role Tools

Typed planner → researcher → implementer → reviewer contracts. Bad transitions or missing payload keys throw at the boundary instead of silently downstream.

ToolDescriptionRequired Params
role_contractGet the typed contract (produces, consumes, allowed handoffs) for a role.role
role_claimStamp a session with an agent role.session_id, role
role_handoffValidate and produce a typed handoff between roles. Throws on illegal transitions or missing keys.from, to, payload