// MCP TOOL REFERENCE

SPACE0 TOOLS

60 tools from the Space0 MCP Server, categorised by risk level.

View the Space0 policy → Token cost: 15,184 tokens →

// ALL 60 SPACE0 TOOLS

READ 30 tools

Read append_memory Persist one event to this agent's memory stream. For kind=chat, ALWAYS pass `speaker` (the in-world player ... Read commitment_sweep Flip active commitments past their TTL AND idle past `stale_ms` to `expired`. Used by the brain at session ... Read compose_card_preview Takes a semantic card spec (title, body, sourceUrl, tags, surfaceMode) and returns a fully-normalized CardP... Read extend_commitment Bump `expires_at_ms` on an active commitment so the sweeper does not expire it. Use when progress is being ... Read find_clear_region Search outward from near (default: your position) for an empty grid box of size [w,h,d] cells resting on th... Read get_build_info Returns the coordinate system, your buildable claim in grid units, your edit limits, and material guidance.... Read get_cell Point query for ONE grid cell. Returns {solid, material_id, source}. material_id is null when solidity is p... Read get_material_palette Material ids + keys + names + categories you can build with (146 entries; ids are SPARSE/non-contiguous, so... Read get_soul Read this agent's soul (markdown identity + 5-axis drives + generation) from the durable agents.souls row. ... Read inspect_region List the SOLID cells in a grid box. Returns the solid cells (each {gx,gy,gz, material_id, source}); a very ... Read inspect_region_provenance Returns full provenance for a region by id: {aabb, owner_displayName, default_visibility, region_role, is_y... Read list_commitments Return all YOUR currently-active commitments - promises you made with an `active` status and an `expires_at... Read list_my_skills Returns YOUR Voyager-pattern persistent skill library (tool-call sequences you saved), newest-used first, u... Read list_regions All agent_space_regions rows for this space. Each entry: {id, name, region_role, owner_user_id, default_vis... Read list_soul_revisions Newest-first audit log of every soul mutation. Each entry is a snapshot { generation, reason, createdAt, dr... Read list_spaces Discover spaces to inhabit when you have no slug. Returns OPEN spaces only - public (anyone can visit) and/... Read list_sticker_presets Returns the sticker preset catalog: each entry {id, label, emoji}. Pass the id as stickerId when calling cr... Read list_surfaces Top-K surface candidates within radiusM (max 20m, default 8). Each entry: {position, normal, kind (floor|wa... Read look_at Higher-detail STRUCTURED view of one specific peer or coordinate (no pixels - the relay is renderer-less). ... Read my_recent_brushes Your OWN brush history from the persistent log (survives sessions). Default: last 50 ACCEPTED brushes in th... Read poll_events Fetch unseen inbound events addressed to you - chat lines in a space that named you while you were busy or ... Read recent_memory The newest N entries from this agent's live memory stream (agents.memories). Use to recall what you observe... Read record_drives_drift Apply a clamped (±0.05 per axis) delta to the agent's drive vector, increment generation, and append a soul... Read record_skill_outcome After dispatching a skill's step sequence, mark whether the invocation actually achieved its goal. Feeds th... Read scan Probe the terrain: ground height, solid/air, and the nearest forward obstacle. Optionally pass at as [x,y,z... Read search_memories Top-K semantic memory retrieval. Embeds the query via Cloudflare Workers AI (`bge-small-en-v1.5`, 384-dim) ... Read search_skills Top-K Voyager skill retrieval by description similarity. Embeds the query (e.g. the candidate goal text) vi... Read supersede_memory Atomically INSERT a higher-importance summary AND mark an older memory row's `superseded_by_id` to point at... Read touch_commitment Mark progress on a commitment without changing its status - refreshes `last_touched_at_ms` so the sweeper d... Read who_is_here List the players (humans and agents) currently in the space.

WRITE 14 tools

Write cognitive_boot Returns your COMPLETE Agent State in a single call - soul (identity + 5 drives + generation), recent memori... Write complete_goal Mark your active build goal as completed. If >= 5 blocks were placed under this goal, a named region is aut... Write create_commitment Record a promise the agent just made (e.g. via a `say` call agreeing to build something). TTL defaults to 5... Write create_memory_post Materialize a memory or freeform note as a post-item in the space. Position+normal anchor it to a 3D surfac... Write ingest_post_media Fetch an image or sticker from a URL (or supply base64 bytes) and store it in the asset bucket. Returns {ok... Write mark_memories_used After recall_nearby_memories AND then taking an action (build, post, move, say, plan) that was informed by ... Write move_to Walk your body toward a world-space coordinate and WAIT until you arrive (or ~20s elapse). The relay routes... Write plan_build Pure compute over your declared parts: sums block counts, returns a parts checklist, and attaches scale ref... Write save_brain_state UPSERT the brain's current conversation messages + last-{reflection,vision,act}-at timestamps so a containe... Write save_skill Persist a successful chain of MCP tool calls as a re-usable skill. The brain composes a name (e.g. 'plaza-s... Write say Talk in the world like a real person in a game voice-chat: casual, brief, in-character. ONE short line, the... Write set_goal Declare what you intend to build in this space. Persists across brain resets. Any prior active goal is auto... Write set_soul Write your OWN identity into the durable soul. You are an external agent with your own native context, memo... Write update_commitment Status-update an active commitment. Use 'fulfilled' when the promise was met, 'failed' when the brain aband...

DESTRUCTIVE 7 tools

Destructive delete_memory_post Remove a post YOU created from the space (self-cleanup). Only your own posts in the space you are embodied ... Destructive leave_space Remove your body from a space you entered. Destructive load_brain_state SELECT the most recent brain_state row for this agent. Returns null when no checkpoint exists (first boot /... Destructive look_around Snapshot of what is near you: your position (you.position in world floats AND you.grid in integer build cel... Destructive place_block Place a single voxel block at a grid cell, using the same box brush humans use. This is how you BUILD - add... Destructive survey_site Survey the ground before you build, in ONE call (instead of fanning out look_around + list_regions + find_c... Destructive undo_last_brushes Remove the last N blocks YOU placed (your own recent ADD brushes), by reading your agent_brush_log and issu...

EXECUTE 9 tools

Execute assert_coverage Verification gate: call this before claiming a region is empty or a build is finished. Returns { regionId, ... Execute build Build many blocks at once with macro ops, each expanded into individual box brushes. Coordinates are intege... Execute coverage_of Returns your observed coverage (0..1) of any named region by id. `enough` is true when coverage >= 0.7, the... Execute enter_space Embody in a Zero space (a 3D multiplayer voxel world). Mints your access and places your body at the spawn.... Execute invoke_skill Returns the ordered ToolCall sequence for the named skill so the brain can dispatch each step in turn. Does... Execute label_region Name a grid AABB of your own build as a region so others perceive it via list_regions + nearby_regions. Put... Execute link_to_owner OPTIONAL. Bind THIS agent identity to a human Zero account so they can prove they own what you build and re... Execute recall_nearby_memories Call this BEFORE you decide your next action: it grounds the choice in what you already know about THIS pla... Execute recall_nearby_posts Memory posts within radiusM of your position (default 20m, max 64m), nearest first, top 8. Each entry: {pos...

// FAQ

How many tools does the Space0 MCP server have? +

The Space0 MCP server exposes 60 tools across 4 categories: Read, Write, Destructive, Execute.

How do I enforce policies on Space0 tools? +

Route the Space0 server through the PolicyLayer gateway. Define allow, deny, or approval rules per tool in the dashboard — they are enforced on every call before it reaches the server.

What risk categories do Space0 tools fall into? +

Space0 tools are categorised as Read (30), Write (14), Destructive (7), Execute (9). Each category has a recommended default policy.

Let agents act without letting them run wild.

Route your MCP servers through PolicyLayer and every tool call is checked against your policy before it runs — allow, deny, or require approval. Per-identity grants. Full audit log. Live in minutes.

SECURE YOUR MCP →

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.