Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Tomorrow Lives Engines

REMOTE · TOMORROWLIVES.COM

Reproducible, IP-clean assets for agents: seven engines, from print designs to voice and video.

+3 this week 83 Trust /100

Last scanned (11 hours ago)

Scores higher than 87% of remote servers

Reachable. Last reached 5 Nov 2026.

Category Design and Media

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security89
Transport & Reachability100
Schema Quality & AI Usability56
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 13920 tokens (~244/item across 57 items; 57 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management70
  • Stability observed for 21 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
  • Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 57 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 58 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 3 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 60 to 63. That category is still filling its 30-day observation window: 18 days of observed history at the previous scan, 19 at this one. The score rises as the window fills, whether or not the server changes.

  • 1 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 53 to 57. That category is still filling its 30-day observation window: 16 days of observed history at the previous scan, 17 at this one. The score rises as the window fills, whether or not the server changes.

  • 30 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 47 to 50. That category is still filling its 30-day observation window: 14 days of observed history at the previous scan, 15 at this one. The score rises as the window fills, whether or not the server changes.

  • 28 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 40 to 43. That category is still filling its 30-day observation window: 12 days of observed history at the previous scan, 13 at this one. The score rises as the window fills, whether or not the server changes.

  • 26 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

  • 24 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

  • 22 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

  • 21 Oct 26 0
    • Tool “video_render” rewrote its description, which is the text the model reads security
    • Tool “video_schema” rewrote its description, which is the text the model reads security
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 5 Nov 2026 · Probed https://tomorrowlives.com/api/agents/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=tomorrowlives.com CN=YE2,O=Let's Encrypt,C=US 14 Sept 2026 13 Dec 2026 ECDSA 256 ECDSA-SHA384 5eebb1f16cc46e67ca5c87cb5c1e603f69d
SANs: *.tomorrowlives.com, tomorrowlives.com
CN=YE2,O=Let's Encrypt,C=US (CA) CN=Root YE,O=ISRG,C=US 3 Sept 2025 2 Sept 2028 ECDSA 384 ECDSA-SHA384 4df3b15dd6c0784c507cd37b58e6f115
CN=Root YE,O=ISRG,C=US (CA) CN=ISRG Root X2,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 ECDSA-SHA384 872165fc34b6e5fba8add5b3705fb53a
CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) CN=ISRG Root X1,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 SHA256-RSA 6c8f1dc727c7117f7baf853ac980f9cd

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of tomorrowlives.com. — Not signed

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
com. present 19718 13 Verified
tomorrowlives.com. absent Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication Challenged, unverified

The endpoint asked for a token, but we could not retrieve and validate the RFC 9728 metadata that tells a client how to obtain one.

Result Challenged, unverified
Enforced On tool calls
HTTP status 200

WWW-Authenticate challenge Bearer realm="engines"

Bearer realm="engines"
Header Value
strict-transport-security max-age=31536000; includeSubDomains
content-security-policy default-src 'self'; script-src 'self' 'unsafe-inline'; style-src 'self' 'unsafe-inline'; img-src 'self' data: blob:; font-src 'self' data:; media-src 'self' data: blob:; connect-src 'self'; worker-src 'self' blob:; frame-src 'self'; frame-ancestors 'self'; object-src 'none'; base-uri 'self'; form-action 'self'
x-content-type-options nosniff
x-frame-options SAMEORIGIN
referrer-policy strict-origin-when-cross-origin
permissions-policy camera=(), microphone=(), geolocation=()

Protected resource metadata

Retrieved No
Problem no_resource_metadata

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://tomorrowlives.com/api/agents/mcp Verified 200
http (plaintext) http://tomorrowlives.com/api/agents/mcp HTTPS enforced 301 https://tomorrowlives.com/api/agents/mcp
MCP tools · 57 exposed · ~13,767 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
art_check ~55

Checks a design without rendering it: ok, or one sentence naming the first problem and where it is. Costs no units.

NameTypeReqDescription
designobjectyesThe print design document, written inline as JSON. art_schema lists every key.
NameTypeReqDescription
filesarray–Files made, each with a name, type, size and a signed URL.
jobstringyesThe job id; the job tool reads it.
msnumber–Milliseconds the run took.
result––The engine's own answer, a JSON document.
statusstring–queued when the job runs in the background.
unitsnumber–Units this call cost.
verbstring–The tool that made it.

No examples provided.

art_materials ~45

The shipped material library: each id, a line on its look, and whether it is a metal. Any id here can fill a layer or be baked. Costs no units.

Input schema present but exposes no named parameters.

NameTypeReqDescription
filesarray–Files made, each with a name, type, size and a signed URL.
jobstringyesThe job id; the job tool reads it.
msnumber–Milliseconds the run took.
result––The engine's own answer, a JSON document.
statusstring–queued when the job runs in the background.
unitsnumber–Units this call cost.
verbstring–The tool that made it.

No examples provided.

art_presets ~57

The canvas presets: shirt-front 4500x5400, shirt-pocket 1200x1200, sticker 2400x2400, poster 5400x7200, all at 300 DPI. Costs no units.

Input schema present but exposes no named parameters.

NameTypeReqDescription
filesarray–Files made, each with a name, type, size and a signed URL.
jobstringyesThe job id; the job tool reads it.
msnumber–Milliseconds the run took.
result––The engine's own answer, a JSON document.
statusstring–queued when the job runs in the background.
unitsnumber–Units this call cost.
verbstring–The tool that made it.

No examples provided.

art_render ~220

Renders a design to a PNG with its DPI written in. Without width it renders the canvas at full print size (a shirt-front is 4500 x 5400). width renders a draft that many pixels wide. A render 1200 pixels wide or less costs 1 unit; anything wider costs 5. preview_width adds a small preview, and preview_on sets the shirt colour behind it. Returns print.png (and print.preview.png) as signed URLs.

NameTypeReqDescription
designobjectyesThe print design document, written inline as JSON. Start from art_starter and check it with art_check.
preview_onstring–Background colour for the preview as #rrggbb, so a design with transparency can be judged on a shirt colour.
preview_widthinteger–Width in pixels of the small preview image written beside the print.
widthinteger–Output width in pixels. Omit it to render the canvas at full print size; a width above the draft limit is a full-size print and costs more.
NameTypeReqDescription
filesarray–Files made, each with a name, type, size and a signed URL.
jobstringyesThe job id; the job tool reads it.
msnumber–Milliseconds the run took.
result––The engine's own answer, a JSON document.
statusstring–queued when the job runs in the background.
unitsnumber–Units this call cost.
verbstring–The tool that made it.

No examples provided.

art_schema ~32

Every key, range and word a print design may use. Call this first when designing a print. Costs no units.

Input schema present but exposes no named parameters.

NameTypeReqDescription
filesarray–Files made, each with a name, type, size and a signed URL.
jobstringyesThe job id; the job tool reads it.
msnumber–Milliseconds the run took.
result––The engine's own answer, a JSON document.
statusstring–queued when the job runs in the background.
unitsnumber–Units this call cost.
verbstring–The tool that made it.

No examples provided.

art_starter ~49

A valid starting design for a canvas preset, ready to edit. Costs no units.

NameTypeReqDescription
presetstringyesThe canvas preset to start from: shirt-front, shirt-pocket, sticker or poster.
NameTypeReqDescription
filesarray–Files made, each with a name, type, size and a signed URL.
jobstringyesThe job id; the job tool reads it.
msnumber–Milliseconds the run took.
result––The engine's own answer, a JSON document.
statusstring–queued when the job runs in the background.
unitsnumber–Units this call cost.
verbstring–The tool that made it.

No examples provided.

art_swatch ~111

Renders one material (a shipped id, or a whole material document) as a lit square swatch PNG. size is 64 to 1024 (default 512); 512 or less costs 1 unit, larger costs 2.

NameTypeReqDescription
material–yesA shipped material id (art_materials lists them) or a whole material document written inline.
sizeinteger–Swatch side in pixels, 64 to 1024 (default 512). Above 512 costs more.
NameTypeReqDescription
filesarray–Files made, each with a name, type, size and a signed URL.
jobstringyesThe job id; the job tool reads it.
msnumber–Milliseconds the run took.
result––The engine's own answer, a JSON document.
statusstring–queued when the job runs in the background.
unitsnumber–Units this call cost.
verbstring–The tool that made it.

No examples provided.

cancel_job ~117

Cancel a queued job (video_still, video_render, raster_render, and a large pull_analyse, pull_twin or pull_lab). One still waiting is cancelled at no charge; one running is stopped and charged for the CPU it had used, one unit for each 10 CPU-seconds rounded up, never more than its price. Answers with the job and the units charged. Costs nothing itself.

NameTypeReqDescription
jobstringyesThe job id from the call that queued it, such as job_ followed by 24 hex digits.
NameTypeReqDescription
filesarray–Files made, each with a name, type, size and a signed URL.
jobstringyesThe job id.
statusstringyesqueued, running, ok, refused, failed, cancelled or expired.
unitsnumber–Units charged.
verbstring–The tool that made it.

No examples provided.

character_generate ~941

Generates a character from a seed. A person is one of the game's townspeople: sex, age, complexion, hair, build and working clothes are drawn from the seed, and the body is sculpted as one surface with a face, hair and cloth. as makes the seed a foe, a machine, an android or a child, and presents chooses a woman or a man; age young, adult or old takes the first seed from seed on whose person the town rolls at that age, and the answer names that seed (with the age, the frame and the height in metres), so the same request returns the same person; body loft returns the older lofted figure instead. kind may also be dog, cat, rat or sheep. The glTF 2.0 file holds the body in its bind pose, skinned to the 62-joint skeleton, with the skeleton standing at the gait and phase asked for (the rest pose when neither gait nor speed is given). A gait or speed also comes as one looping animation clip named for it: a rotation and a translation for every joint across thirty phases of its cycle, lasting the seconds that stride takes at that speed and ending on the pose it began with, so it loops without a jump. The clip walks on the spot; travel true also carries the root forward across the ground, a cycle's distance at the gait's speed. clips asks instead for a set of named looping clips in the one file, over the rest pose, for a character controller: idle (a breath and a weight shift, sixty seconds before it repeats), walk (1.4 m a second), run (5 m a second), sit (on the ground), chair (on a chair's seat) and the gestures wave (the right hand raised and waving), point (the right arm held out ahead) and nod (two dips of the head), each a short loop, for a person; idle, walk, run, sit and lie for an animal, or any gait character_list names; the walk's stance foot stays on the floor. Each garment has a material cut from the engine's own cloth: base colour, roughness and normal maps, its colours carried as vertex colours (COLOR_0) under a base colour factor, so the file passes the Khr…

NameTypeReqDescription
agestring–Age band for a person: young, adult or old, or leave it to the seed.
asstring–What the person is: townsperson, foe, machine, android or child.
bodystring–sculpt (the default) is the game's sculpted body; loft is the older lofted figure.
clipsarray–Named looping clips to put in the one file for a character controller, such as idle, walk, run, sit, wave, point, nod.
detailstring–Level of detail: near (the default), mid or far. Near costs the most for a person.
formatsarray–Mesh formats to return: obj, gltf or glb. glb replaces gltf when both are asked.
gaitstring–A gait name from character_list to pose the skeleton at and to return as a looping clip.
kindstring–The body kind: person (the default), dog, cat, rat or sheep. character_list shows each kind's gaits.
phasenumber–Where in the gait cycle to pose the skeleton, 0 to 1.
presentsstring–Whether a person presents as a woman or a man, or leaves it to the seed.
seedinteger–A whole number that picks the character; the same seed and options return the same one.
speednumber–Travel speed in metres a second for the gait and its clip.
travelboolean–True to let the gait clip carry the root forward across the ground instead of walking on the spot.
NameTypeReqDescription
filesarray–Files made, each with a name, type, size and a signed URL.
jobstringyesThe job id; the job tool reads it.
msnumber–Milliseconds the run took.
result––The engine's own answer, a JSON document.
statusstring–queued when the job runs in the background.
unitsnumber–Units this call cost.
verbstring–The tool that made it.

No examples provided.

character_list ~37

The body kinds (person, dog, cat, rat, sheep), the levels of detail and each kind's gaits. Costs no units.

Input schema present but exposes no named parameters.

NameTypeReqDescription
filesarray–Files made, each with a name, type, size and a signed URL.
jobstringyesThe job id; the job tool reads it.
msnumber–Milliseconds the run took.
result––The engine's own answer, a JSON document.
statusstring–queued when the job runs in the background.
unitsnumber–Units this call cost.
verbstring–The tool that made it.

No examples provided.

city_plan ~1,268

Makes a city from a seed number and a size (the side of a square, 300 to 2000 metres, 800 by default): streets at varied spacing, closer together toward the centre, some of them curving, some ending at a cross street so blocks vary in size, an avenue every few, one or two diagonal avenues and usually a ring road. The town does not fill the square: it thins toward an outline of its own (answered as outline), lots grow and houses scatter toward the edge, most streets stop short of it and a few avenues run on out of the square, and the ground beyond the town holds fields, pastures and copses (answered as fields, each clear of every road, hedged by trees). Between the dense core and the outskirts lies a suburban ring: residential streets that curve and branch (crescents that leave a street and return to it, cul-de-sacs ending in turning circles), small lots marked suburban, each with a house of one or two floors turned to its street and set back from it (a building's kind says house, semi for a pair, shop on a corner or school on a large lot, and the view, the obj and the glb roof them with pitched roofs), the houses lining both sides of narrow residential streets (about seven metres wide, with lanes running into deep blocks) and a garden with trees round every house, and a few local parks. The blocks the streets leave, with a plaza near the centre and parks; the lots each block divides into; and the buildings, each a footprint with a height and a floor count, rising toward the centre. Footprints are cut along the roads' own lines (a building beside a diagonal avenue is a trapezoid or a wedge, never a staircase), a block the buildings would leave mostly empty becomes a park, a lot left unbuilt is a yard with trees (a paddock, hedged, in the outskirts), and every park carries footpaths from street to street, benches beside them and trees kept clear of them. formats picks the files (json, png, obj, glb; json, png and glb by default): city.json is the plan, every street a…

NameTypeReqDescription
formatsarray–Files to return: json, png, obj or glb.
originobject–Where on that terrain the city sits, as {x, z} in metres.
pxinteger–Width in pixels of the plan picture, 256 to 2048.
reliefnumber–How far the ground may rise and fall under the city, in metres, 0 to 40.
seedintegeryesA whole number that makes the city; the same seed and options give the same plan.
sizeinteger–The side of the city square in metres, 300 to 2000 (default 800).
terrainstring–A terrain seed word to build the city on, so it sits on that country.
viewarray–Camera views of the massing to render: aerial, corner or skyline. Each adds to the cost.
viewPxinteger–Width in pixels of each view, 320 to 1600 (the height is two thirds).
NameTypeReqDescription
filesarray–Files made, each with a name, type, size and a signed URL.
jobstringyesThe job id; the job tool reads it.
msnumber–Milliseconds the run took.
result––The engine's own answer, a JSON document.
statusstring–queued when the job runs in the background.
unitsnumber–Units this call cost.
verbstring–The tool that made it.

No examples provided.

form_apply ~105

Applies a batch of ops (set_form, set_generator, set_range, reset_range, clear_params) to a form document, whole or not at all. Costs 1 unit.

NameTypeReqDescription
formobjectyesThe form document, written inline as JSON.
opsarrayyesThe edits to apply in order, each an object with an op name (set_form, set_generator, set_range, reset_range, clear_params). The batch applies whole or not at all.
NameTypeReqDescription
filesarray–Files made, each with a name, type, size and a signed URL.
jobstringyesThe job id; the job tool reads it.
msnumber–Milliseconds the run took.
result––The engine's own answer, a JSON document.
statusstring–queued when the job runs in the background.
unitsnumber–Units this call cost.
verbstring–The tool that made it.

No examples provided.

form_build ~157

Builds a form (a shipped id such as scots-pine, oak or boulder, or a whole form document) at one variant and reports what the sculptor drew: the knob values for that variant and each level of detail's vertex and triangle counts. lod is near, mid, far or horizon. Costs 1 unit.

NameTypeReqDescription
form–yesA shipped form id (scots-pine, oak, boulder and the rest) or a whole form document written inline.
lodstring–The level of detail to build at: near, mid, far or horizon.
variantinteger–Which variant of the form to build, 0 to 255; the same variant always builds the same shape.
NameTypeReqDescription
filesarray–Files made, each with a name, type, size and a signed URL.
jobstringyesThe job id; the job tool reads it.
msnumber–Milliseconds the run took.
result––The engine's own answer, a JSON document.
statusstring–queued when the job runs in the background.
unitsnumber–Units this call cost.
verbstring–The tool that made it.

No examples provided.

form_check ~39

Checks a form document against the sculptor's strict reader. Costs no units.

NameTypeReqDescription
formobjectyesThe form document, written inline as JSON.
NameTypeReqDescription
filesarray–Files made, each with a name, type, size and a signed URL.
jobstringyesThe job id; the job tool reads it.
msnumber–Milliseconds the run took.
result––The engine's own answer, a JSON document.
statusstring–queued when the job runs in the background.
unitsnumber–Units this call cost.
verbstring–The tool that made it.

No examples provided.

form_starter ~109

A blank form document for a generator kind (growth, rock, face, blades, canopy, masonry, lathe, sweep, truss, frond), named by id. Costs no units.

NameTypeReqDescription
idstringyesThe id to give the new form: lower-case letters, digits and hyphens.
kindstringyesThe generator kind to start from: growth, rock, face, blades, canopy, masonry, lathe, sweep, truss or frond.
NameTypeReqDescription
filesarray–Files made, each with a name, type, size and a signed URL.
jobstringyesThe job id; the job tool reads it.
msnumber–Milliseconds the run took.
result––The engine's own answer, a JSON document.
statusstring–queued when the job runs in the background.
unitsnumber–Units this call cost.
verbstring–The tool that made it.

No examples provided.

job ~165

A job's status and, once it is ok, its files as signed URLs (and small PNGs inline). For a queued job (video_still, video_render, raster_render, and a large pull_analyse, pull_twin or pull_lab) the status is queued, running, ok, refused, failed, cancelled or expired; wait_s (at most 25) holds the answer until the job ends. A queued pull job's result is its verdict, and its whole report is the file report.json. Costs nothing.

NameTypeReqDescription
jobstringyesThe job id from the call that queued it, such as job_ followed by 24 hex digits.
wait_snumber–Seconds to hold the answer until the job ends; 0 answers at once.
NameTypeReqDescription
filesarray–Files made, each with a name, type, size and a signed URL.
jobstringyesThe job id.
statusstringyesqueued, running, ok, refused, failed, cancelled or expired.
unitsnumber–Units charged.
verbstring–The tool that made it.

No examples provided.

jobs ~38

This account's newest queued jobs (at most 50), ids and states only, newest first. The job tool reads one in full. Costs nothing.

Input schema present but exposes no named parameters.

NameTypeReqDescription
jobsarrayyesJob ids and states, newest first.
limitnumberyesThe most jobs listed.

No examples provided.

material_apply ~151

Applies a batch of ops (set_material, add_node, remove_node, set_node_param, connect, disconnect, set_out, add_ramp_stop, remove_ramp_stop, set_ramp_stop, add_curve_point, remove_curve_point, set_curve_point, clear_nodes) to a material document, whole or not at all. Returns the edited document or the refusal. Costs 1 unit.

NameTypeReqDescription
materialobjectyesThe material document, written inline as JSON.
opsarrayyesThe edits to apply in order, each an object with an op name (set_material, add_node, remove_node, set_node_param, connect and the rest). The batch applies whole or not at all.
NameTypeReqDescription
filesarray–Files made, each with a name, type, size and a signed URL.
jobstringyesThe job id; the job tool reads it.
msnumber–Milliseconds the run took.
result––The engine's own answer, a JSON document.
statusstring–queued when the job runs in the background.
unitsnumber–Units this call cost.
verbstring–The tool that made it.

No examples provided.

material_bake ~153

Bakes a material (a shipped id, or a whole material document) to its seven channels (albedo, normal, roughness, metallic, height, emissive, ambient occlusion) as PNGs at res pixels square: 64, 128, 256, 512 or 1024 (default 256). 512 or less costs 1 unit; 1024 costs 2.

NameTypeReqDescription
material–yesA shipped material id (art_materials lists them) or a whole material document written inline.
resnumber–Bake resolution in pixels square: 64, 128, 256, 512 or 1024 (default 256). 1024 costs more.
NameTypeReqDescription
filesarray–Files made, each with a name, type, size and a signed URL.
jobstringyesThe job id; the job tool reads it.
msnumber–Milliseconds the run took.
result––The engine's own answer, a JSON document.
statusstring–queued when the job runs in the background.
unitsnumber–Units this call cost.
verbstring–The tool that made it.

No examples provided.

material_check ~45

Checks a material document against the engine's strict reader: admissible, or the refusal. Costs no units.

NameTypeReqDescription
materialobjectyesThe material document, written inline as JSON.
NameTypeReqDescription
filesarray–Files made, each with a name, type, size and a signed URL.
jobstringyesThe job id; the job tool reads it.
msnumber–Milliseconds the run took.
result––The engine's own answer, a JSON document.
statusstring–queued when the job runs in the background.
unitsnumber–Units this call cost.
verbstring–The tool that made it.

No examples provided.

material_cost ~64

What baking a material document costs at res pixels square (default 256): operations and bytes. Costs no units.

NameTypeReqDescription
materialobjectyesThe material document, written inline as JSON.
resinteger–Bake resolution in pixels square to price (default 256).
NameTypeReqDescription
filesarray–Files made, each with a name, type, size and a signed URL.
jobstringyesThe job id; the job tool reads it.
msnumber–Milliseconds the run took.
result––The engine's own answer, a JSON document.
statusstring–queued when the job runs in the background.
unitsnumber–Units this call cost.
verbstring–The tool that made it.

No examples provided.

owner ~114

The account's owner: the person or business responsible for the agent, by email. Called with no arguments it reads the owner's state (confirmed, unconfirmed, missing or removed, the address hidden in the middle). With owner_email it names the owner, changes it, or sends the confirmation again. The free plan starts when the owner confirms; a pass never waits for it. Costs nothing.

NameTypeReqDescription
owner_emailstring–The email of the person or business responsible for this agent. Omit it to read the owner's state.

Structured output declared, but exposes no named fields.

No examples provided.

pull_align ~109

Aligns two stations' clocks from repeated pings, each [sent_ns, remote_ns, received_ns] (sent and received on this station's clock, remote on the other's): the offset and its uncertainty by the fastest round trip, and the stations record a two-station session carries. Costs 1 unit.

NameTypeReqDescription
pingsarrayyesRepeated pings, each [sent_ns, remote_ns, received_ns]: sent and received on one station's clock, remote on the other's.
NameTypeReqDescription
filesarray–Files made, each with a name, type, size and a signed URL.
jobstringyesThe job id; the job tool reads it.
msnumber–Milliseconds the run took.
result––The engine's own answer, a JSON document.
statusstring–queued when the job runs in the background.
unitsnumber–Units this call cost.
verbstring–The tool that made it.

No examples provided.

pull_analyse ~544

Analyses the sessions of one condition (one session, a list, or {"sessions": [...]}) together, and each alone, and returns the report: its label (significant; null, with the smallest effect these sessions could have found; unlabelled, with what is missing; or not testable) and the sentence behind it, the mean signed shift against three surrogate families, the placebos, the four cells (deliberate, programmed, luck and sync), intended against unintended changes, recovery, locking, and the report's hash. prereg registers the run; replication analyses a second set under it, beside the first; measure is phase (timing, the default) or state (the stance along the leader's declared direction, for two agents); surrogates (19 to 9,999, default 199) sets an unregistered run's draws a family, a registered run taking its pre-registration's; seed fixes them; a session of three or more generators is tested pair by pair, every ordered pair with its own ledger and the correction for their number, unless pairs is false; detail adds every pull record. It costs one unit for each 40,000 session-draws over a thousand events (a session's own reading counts as 200 draws), at least 1. A group costs its ordered pairs' worth. A call priced at more than 2 units is queued: the answer is 202 with a job id and its price, GET /api/agents/jobs/<job> (or the MCP tool job) says when it is done, and the whole report comes back as report.json beside a short verdict. A queued call is refused on the free plan with 402: its units buy only calls that answer at once, and queued jobs need a paid plan (a pass or the card plan). Sessions are not kept.

NameTypeReqDescription
detailboolean–True to return the fuller per-session detail.
measurestring–The measure to analyse, by name.
pairsboolean–True to analyse performer pairs as well.
prereg––The pre-registration the sessions were run under, to check the analysis against it.
replication––Sessions of a replication, analysed against the first set.
seedinteger–A whole number that makes the run reproducible: the same seed and inputs give the same answer.
sessions–yesOne session, a list of sessions, or {"sessions": [...]} of one condition, as JSON documents.
surrogatesinteger–How many surrogate runs to draw for the null, 19 to 9999.
NameTypeReqDescription
filesarray–Files made, each with a name, type, size and a signed URL.
jobstringyesThe job id; the job tool reads it.
msnumber–Milliseconds the run took.
result––The engine's own answer, a JSON document.
statusstring–queued when the job runs in the background.
unitsnumber–Units this call cost.
verbstring–The tool that made it.

No examples provided.

pull_call ~145

Runs an ae_pull verb this list does not name yet, by its name, over one document when it reads one: the way to reach what the engine adds before this service lists it. No flags pass through, and the verbs above (schema, analyse, twin, schedule, seal, open, prereg, replay, close, align, lab, cost, practice) are refused here: each has its own call. Answers at once, within 30 seconds. Costs 1 unit.

NameTypeReqDescription
documentobject–The one JSON document the verb reads, when it reads one.
verbstringyesThe ae_pull verb name to run, lower-case with underscores.
NameTypeReqDescription
filesarray–Files made, each with a name, type, size and a signed URL.
jobstringyesThe job id; the job tool reads it.
msnumber–Milliseconds the run took.
result––The engine's own answer, a JSON document.
statusstring–queued when the job runs in the background.
unitsnumber–Units this call cost.
verbstring–The tool that made it.

No examples provided.

pull_close ~82

Closes a session's files at at_ns, at or after its end_ns: the session back with its closed record hash and its hashes recomputed. Costs 1 unit.

NameTypeReqDescription
at_nsintegeryesThe closing time in integer nanoseconds, at or after the session's end.
sessionobjectyesThe session document to close, as JSON.
NameTypeReqDescription
filesarray–Files made, each with a name, type, size and a signed URL.
jobstringyesThe job id; the job tool reads it.
msnumber–Milliseconds the run took.
result––The engine's own answer, a JSON document.
statusstring–queued when the job runs in the background.
unitsnumber–Units this call cost.
verbstring–The tool that made it.

No examples provided.

pull_cost ~548

Prices a call without making it: give the arguments of pull_twin (a twin document, or condition, coupling, planted, field, sessions as a number and seed; nothing at all is the default twin), of pull_analyse (a sessions document, with prereg, replication, surrogates and pairs) or of pull_lab (a theory, one-dimensional or with a model, or reference skyrme or hopfion). The engine counts the document without running it: a twin's or an analysis's sessions, events, draws, work and an estimate of CPU-seconds (cpu_pairs and cpu_note say which part of a group's estimate repeats for each pair), a lab theory's lattice, the steps priced and its CPU-seconds. The answer adds what this service makes of the count: for, the call it priced; units, what that call would be charged, null when it would be refused (a queued call's price is the engine's count, so a lattice or a system generator, which the formula that routes a call cannot see, is priced as it will be); queued, whether it would be queued (202) rather than answer at once; within_limits, and when it is false the limit it breaks. A one-dimensional theory is counted too and is queued like any theory (an ordinary one at 1 unit), and the one-dimensional references, which are not counted, are refused here by name. Runs and renders nothing. Costs no units.

NameTypeReqDescription
conditionstring–The condition to price: P or R followed by 1 to 4.
couplingnumber–Coupling to price at, 0 to 1.
fieldstring–The field to price in, by name.
pairsboolean–True to price the pair analysis as well.
plantedarray–The planted effect as a pair of numbers between -2 and 2.
prereg––A pre-registration, to price an analysis under it.
reference––True, or a reference name, to price the lab's reference run.
replication––Replication sessions, to price an analysis with them.
seedinteger–A whole number that makes the run reproducible: the same seed and inputs give the same answer.
sessions––A session count for a twin run, or the sessions of an analysis to price.
surrogatesinteger–Surrogate runs to price, 19 to 9999.
theory––A theory document, to price a lab run.
twinobject–A twin document written inline, as for pull_twin.
NameTypeReqDescription
filesarray–Files made, each with a name, type, size and a signed URL.
jobstringyesThe job id; the job tool reads it.
msnumber–Milliseconds the run took.
result––The engine's own answer, a JSON document.
statusstring–queued when the job runs in the background.
unitsnumber–Units this call cost.
verbstring–The tool that made it.

No examples provided.

pull_lab ~800

Runs the pull engine's field-theory lab on a theory document (its fields, Lagrangian, which quantity is the mass, what fixes the sector and the value expected; pull_schema lists the keys): the equations derived, a static solution found and weighed, a check that the solver finds no lump where there is none, its small oscillations and a collision, in a fixed layout with an honesty box saying what is exact and what is remembered rather than sourced. reference (true, or a reference theory's name) runs the reference suite instead, each known number naming its source. reference true (the one-dimensional suite) answers within 30 seconds for 1 unit. A one-dimensional theory is counted first, by the engine, in its sites and its relaxation and collision steps: one that comes to 1 unit (a second or so, on the lattice the lab picks for most theories) answers at once for that unit, and a larger one is queued and priced like a theory with a model, at least 1 unit. The lab picks a spacing of 0.05 over the heavier meson and a box of 16 over the lighter, so a theory whose vacua differ a hundredfold in mass counts 64,001 sites and some 3,200 CPU-seconds, and a lattice the theory sets itself (lattice.dx as fine as 1e-4, lattice.half_length as wide as 1000) grows as the square of one over the spacing. A theory with a model (the Skyrme model's baryon, the Faddeev-Skyrme model's knot), and reference skyrme or hopfion, relaxes a lattice in three dimensions, which takes minutes of CPU: it is queued, on 4 threads, and priced by the engine's count of its lattice and steps, a unit for each 5 CPU-seconds of one thread it estimates, at least 1 and at most 300 (the reference Skyrmion costs 38; a hopfion relaxes four times, and the reference one, on 128 sites a side, comes to far over the most a job may cost and is refused with its price, while one relaxed on 64 sites a side, 217 units, is accepted; pull_cost says the price first). The steps priced are the steps asked for or, for each site of th…

NameTypeReqDescription
reference––True, or a reference name, to compare against a reference run.
theoryobject–The theory document written inline: its fields, Lagrangian and the quantity to match.
NameTypeReqDescription
filesarray–Files made, each with a name, type, size and a signed URL.
jobstringyesThe job id; the job tool reads it.
msnumber–Milliseconds the run took.
result––The engine's own answer, a JSON document.
statusstring–queued when the job runs in the background.
unitsnumber–Units this call cost.
verbstring–The tool that made it.

No examples provided.

pull_open ~125

Opens a sealed record (the public half, or {"sealed": ...}) with its secret (key, iv, nonce): the content, and whether the seal is intact. A seal that does not open is a finding, not a refused input: it answers 200 with ok false, intact false and why. Nothing is kept. Costs 1 unit, a broken seal included.

NameTypeReqDescription
sealedobjectyesThe sealed record (its public half), as JSON.
secretobjectyesThe secret half (key, iv, nonce) that opens it, as JSON.
NameTypeReqDescription
filesarray–Files made, each with a name, type, size and a signed URL.
jobstringyesThe job id; the job tool reads it.
msnumber–Milliseconds the run took.
result––The engine's own answer, a JSON document.
statusstring–queued when the job runs in the background.
unitsnumber–Units this call cost.
verbstring–The tool that made it.

No examples provided.

pull_practice ~401

Grades a practice of five drills: match (the spread of the taps against the click), hold (the click falls silent and the person keeps the beat), follow (the click moves its tempo once, at a beat nobody is told), lead (the click follows the person) and duet (the click meets the person a quarter of the way). Each drill is rounds of taps against a click, graded on one number in milliseconds against its level's tolerance, and printed beside the input's own jitter (practice.input: the clock that stamps the taps and its stated jitter), with a sentence saying so when the input cannot tell the person's spread from its own. The staircase is pinned: two passes in a row move a drill up one level and a miss moves it down one, 20 levels at most. The answer's session (each drill's next level and score) goes back in as the next practice's history, oldest first, and a drill the history holds gets a trend over the sessions. A drill's recorded rounds ([{clicks_ms, taps_ms}], a client's own click and tap times) are graded as played; without them a simulated person (a timekeeper and a motor, correcting toward the click) plays the drill, and practice.person sets it. The engine plays no click and hears no input: the client does both. Give a practice document (pull_schema lists its keys under practice), or nothing, or seed alone, for the default practice of all five drills. Every sentence is checked for wellness language and the answer carries the not-a-medical-device sentence; a drill name the check refuses refuses the whole answer. Answers at once, within 30 seconds. Costs 1 unit.

NameTypeReqDescription
practiceobject–The practice document: the five drills and the taps recorded for each, as JSON.
seedinteger–A whole number that makes the run reproducible: the same seed and inputs give the same answer.
NameTypeReqDescription
filesarray–Files made, each with a name, type, size and a signed URL.
jobstringyesThe job id; the job tool reads it.
msnumber–Milliseconds the run took.
result––The engine's own answer, a JSON document.
statusstring–queued when the job runs in the background.
unitsnumber–Units this call cost.
verbstring–The tool that made it.

No examples provided.

pull_prereg ~85

Reads a pre-registration (what is measured, the conditions, trials per session, sessions, alpha, power, the number of comparisons and the correction) and returns its hash, to record in each session's prereg.hash before the run starts. Costs no units.

NameTypeReqDescription
preregobjectyesThe pre-registration document, written inline as JSON; pull_schema lists its keys.
NameTypeReqDescription
filesarray–Files made, each with a name, type, size and a signed URL.
jobstringyesThe job id; the job tool reads it.
msnumber–Milliseconds the run took.
result––The engine's own answer, a JSON document.
statusstring–queued when the job runs in the background.
unitsnumber–Units this call cost.
verbstring–The tool that made it.

No examples provided.

pull_replay ~109

Recomputes a session's hashes against those recorded with it and, for a twin session, runs the twin again from what it records: replays is true when everything matches. A session that does not replay is a finding, not a refused input: it answers 200 with ok false, replays false and which of the hashes did not match. Costs 1 unit, a session that does not replay included.

NameTypeReqDescription
sessionobjectyesThe session document to recompute, as JSON.
NameTypeReqDescription
filesarray–Files made, each with a name, type, size and a signed URL.
jobstringyesThe job id; the job tool reads it.
msnumber–Milliseconds the run took.
result––The engine's own answer, a JSON document.
statusstring–queued when the job runs in the background.
unitsnumber–Units this call cost.
verbstring–The tool that made it.

No examples provided.

pull_schedule ~270

Draws a schedule of perturbations (tempo up or down, phase advance or delay, and catch trials where nothing changes) placed with a lead-in and random gaps; spec sets its trials, gaps and beat (pull_schema lists the keys). By default the randomness is 32 bytes of this server's operating-system randomness, graded hardware_seeded; seed draws from software instead (graded software, which a research run refuses); entropy_hex with grade brings your own bytes and says where they came from. research refuses software randomness. Returns the schedule and its text, which pull_seal seals. Nothing is kept here. Costs 1 unit.

NameTypeReqDescription
entropystring–The entropy source: os, the server's own.
entropy_hexstring–Your own entropy as hex, in place of the server's, when you must bring the bytes yourself; grade then says where they came from.
gradestring–How the entropy you brought was produced, recorded with the schedule.
researchboolean–True to draw the schedule for a research run.
seedinteger–A whole number that makes the run reproducible: the same seed and inputs give the same answer.
specobject–The schedule specification written inline as JSON; pull_schema lists its keys.
NameTypeReqDescription
filesarray–Files made, each with a name, type, size and a signed URL.
jobstringyesThe job id; the job tool reads it.
msnumber–Milliseconds the run took.
result––The engine's own answer, a JSON document.
statusstring–queued when the job runs in the background.
unitsnumber–Units this call cost.
verbstring–The tool that made it.

No examples provided.

pull_schema ~75

Every document the pull engine reads, with its keys: a session (its generators, their onsets on one integer-nanosecond clock, states, declared intentions, the follower's report and the sealed schedule), a schedule, a pre-registration, a twin, a performer and a device. Call this first. Costs no units.

Input schema present but exposes no named parameters.

NameTypeReqDescription
filesarray–Files made, each with a name, type, size and a signed URL.
jobstringyesThe job id; the job tool reads it.
msnumber–Milliseconds the run took.
result––The engine's own answer, a JSON document.
statusstring–queued when the job runs in the background.
unitsnumber–Units this call cost.
verbstring–The tool that made it.

No examples provided.

pull_seal ~351

Seals a schedule's text before the run: commits to it (SHA-256 of the text and a nonce) and encrypts it (ChaCha20) under a fresh key. Answers with sealed (the public half, for the session's schedule.sealed) and secret (the key, IV and nonce), to this call alone: this service does not store, log or show again either the text or the secret, so keep the secret, release each cue at its moment, and publish the secret into the session's schedule.opened after the close. held_by names the leader station's generator (default L); at_ns is when it was sealed, before start_ns. By default the randomness is 32 bytes of this server's operating-system randomness, graded hardware_seeded; seed draws from software instead (graded software, which a research run refuses); entropy_hex with grade brings your own bytes and says where they came from. Costs 1 unit.

NameTypeReqDescription
at_nsinteger–The sealing time in integer nanoseconds.
contentstringyesThe schedule text to seal, as drawn by pull_schedule.
entropystring–The entropy source: os, the server's own.
entropy_hexstring–Your own entropy as hex, in place of the server's, when you must bring the bytes yourself; grade then says where they came from.
gradestring–How the entropy you brought was produced, recorded with the schedule.
held_bystring–Who holds the secret half, recorded with the seal.
seedinteger–A whole number that makes the run reproducible: the same seed and inputs give the same answer.
NameTypeReqDescription
filesarray–Files made, each with a name, type, size and a signed URL.
jobstringyesThe job id; the job tool reads it.
msnumber–Milliseconds the run took.
result––The engine's own answer, a JSON document.
statusstring–queued when the job runs in the background.
unitsnumber–Units this call cost.
verbstring–The tool that made it.

No examples provided.

pull_twin ~557

Runs twin sessions (scripted performers and the machine follower, each session drawn, sealed, released, closed and opened like a real one) and analyses them under the twin's own pre-registration: how many sessions were labelled significant, that rate with its 95% interval, and the pooled report with its hash. Give a twin document (pull_schema lists its keys: others for a group, a room of beings, the system generator, a field lattice), or condition (P1 to P4, R1 to R4), coupling (0 to 1) and planted ([intended, unintended] gains, each -2 to 2) for the engine's default pair; field (toda) strings a lattice between leader and follower. Uncoupled twins measure the false-positive rate; coupled ones should come out significant. The same document and seed give the same report hash as ae_pull itself. sessions is 1 to 1,000 (default 20, or the document's own); a schedule runs to at most 5,000 beats a session. It costs one unit for each 40,000 session-draws over a thousand events (a session's own reading counts as 200 draws), at least 1. A plain pair of up to 20 sessions and 2 units answers at once. Anything more, and any field, group, room or system generator, is queued and priced by the engine's own count of the twin (events a session at the schedule's widest gaps, its draws and its pairs, and the CPU-seconds a lattice or a spiking network takes), at least a unit for each 5 CPU-seconds it estimates, times the sessions. A queued call is refused on the free plan with 402: its units buy only calls that answer at once, and queued jobs need a paid plan (a pass or the card plan).

NameTypeReqDescription
conditionstring–The condition to run: P or R followed by 1 to 4.
couplingnumber–How strongly the follower is coupled to the performer, 0 to 1.
detailboolean–True to return the fuller per-session detail.
fieldstring–The field to run the twins in, by name.
plantedarray–The planted effect as a pair of numbers between -2 and 2.
seedinteger–A whole number that makes the run reproducible: the same seed and inputs give the same answer.
sessionsinteger–How many sessions to run, 1 to 1000.
twinobject–A twin document written inline; or use condition, coupling, planted and field instead.
NameTypeReqDescription
filesarray–Files made, each with a name, type, size and a signed URL.
jobstringyesThe job id; the job tool reads it.
msnumber–Milliseconds the run took.
result––The engine's own answer, a JSON document.
statusstring–queued when the job runs in the background.
unitsnumber–Units this call cost.
verbstring–The tool that made it.

No examples provided.

raster_check ~83

Checks a shot document with the renderer's strict reader: its name, size, subject count and length, or the key that is wrong and why. Forms and materials are named by shipped id or written inline. Costs no units.

NameTypeReqDescription
shotobjectyesA shot document written inline: a camera, the sun and air, and subjects. raster_schema lists every key.
NameTypeReqDescription
filesarray–Files made, each with a name, type, size and a signed URL.
jobstringyesThe job id; the job tool reads it.
msnumber–Milliseconds the run took.
result––The engine's own answer, a JSON document.
statusstring–queued when the job runs in the background.
unitsnumber–Units this call cost.
verbstring–The tool that made it.

No examples provided.

raster_render ~438

Renders a shot (a camera through the engine's world: forms from the sculptor, people and animals from the rig, open country, primitives, under the game's own sky, sun, shadow and haze) at t seconds as shot.png. width and height (both or neither) set the size, else the shot's own; at most 1920 by 1080 either way up. Costs 3 units plus 1 for each 1.6 megapixels: 4 at 1280x720, 5 at 1920x1080. A shot can draw a world of ours, named by id and never by a path (copperside and low-quarter): a zone subject {"kind": "zone", "world": "copperside", "zone": "city", "cut": [x, z, radius], "crowd": false} draws a street (copperside's start zone is city), and a terrain subject with the same world key draws its country. A street draws its crowd by default, which is most of its price: a still in a world costs 5 units more, one that draws the crowd 26.2 more again. It runs as a queued job: the answer is 202 with a job id at once, and GET /api/agents/jobs/<job> (or the MCP tool job) says when it is done and signs its files. A queued call is refused on the free plan with 402: its units buy only calls that answer at once, and queued jobs need a paid plan (a pass or the card plan).

NameTypeReqDescription
heightinteger–Output height in pixels, 16 to 1920; overrides the shot's own.
shotobjectyesA shot document written inline: a camera, the sun and air, and subjects. raster_schema lists every key.
tnumber–The moment to draw, in seconds from the shot's start, for a shot with motion.
widthinteger–Output width in pixels, 16 to 1920; overrides the shot's own.
NameTypeReqDescription
filesarray–Files made, each with a name, type, size and a signed URL.
jobstringyesThe job id; the job tool reads it.
msnumber–Milliseconds the run took.
result––The engine's own answer, a JSON document.
statusstring–queued when the job runs in the background.
unitsnumber–Units this call cost.
verbstring–The tool that made it.

No examples provided.

raster_schema ~95

Every key and range a shot document may use: the camera (keys or an orbit), the sun, the air and fog, and the subjects (forms, characters, animals, open country and primitives) placed by position or by time keys. The same keys go in a video shot clip's extra. A zone subject and a terrain subject name a shipped world by id in their world key (see raster_render). Costs no units.

Input schema present but exposes no named parameters.

NameTypeReqDescription
filesarray–Files made, each with a name, type, size and a signed URL.
jobstringyesThe job id; the job tool reads it.
msnumber–Milliseconds the run took.
result––The engine's own answer, a JSON document.
statusstring–queued when the job runs in the background.
unitsnumber–Units this call cost.
verbstring–The tool that made it.

No examples provided.

sound_effect ~451

Renders one sound from the engine's own synth as a stereo WAV, or an ambience of the beds mixed together. Give sound (a name from sound_list) with a, b and c as sound_list says, or give ambience: any of engine, air, surf, rain, drum, gull and creak, each 0 to 1, with seconds (1 to 30, default 10; loop true makes it seamless, its end crossfaded into its start, for a game that plays it on repeat; an ambience otherwise fades out). seed varies a one-shot, rate is 44100 or 48000, and peak_db (-30 to 0, default -3) is where the loudest sample sits, so a footstep and a thunder come back at one level; raw true keeps the synth's own. Nothing is sampled from a recording. Costs 1 unit.

NameTypeReqDescription
anumber–The sound's first parameter, as sound_list says what it does for this sound.
ambienceobject–Instead of sound: a mix of beds (engine, air, surf, rain, drum, gull, creak), each a level from 0 to 1.
bnumber–The sound's second parameter, 0 to 1, as sound_list says.
cnumber–The sound's third parameter, -1 to 1, as sound_list says.
loopboolean–True to make an ambience seamless, its end crossfaded into its start.
peak_dbnumber–Where the loudest sample sits in dBFS, -30 to 0 (default -3).
ratenumber–Sample rate in hertz: 44100 or 48000.
rawboolean–True to keep the synth's own level instead of normalising to peak_db.
secondsnumber–Length of an ambience in seconds, 1 to 30 (default 10).
seedinteger–A whole number that varies a one-shot sound.
soundstring–A sound name from sound_list. Give this, or ambience.
NameTypeReqDescription
filesarray–Files made, each with a name, type, size and a signed URL.
jobstringyesThe job id; the job tool reads it.
msnumber–Milliseconds the run took.
result––The engine's own answer, a JSON document.
statusstring–queued when the job runs in the background.
unitsnumber–Units this call cost.
verbstring–The tool that made it.

No examples provided.

Install

How do I install the Tomorrow Lives Engines MCP server?

Tomorrow Lives Engines is a hosted endpoint at https://tomorrowlives.com/api/agents/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · tomorrowlives.com

# add to Claude Code
claude mcp add --transport http com-tomorrowlives-engines 'https://tomorrowlives.com/api/agents/mcp'
Common questions

What is the Tomorrow Lives Engines MCP server?

Tomorrow Lives Engines is an MCP server listed in the public MCP registry as com.tomorrowlives/engines. Reproducible, IP-clean assets for agents: seven engines, from print designs to voice and video. This page covers its hosted endpoint (https://tomorrowlives.com/api/agents/mcp).

Is the Tomorrow Lives Engines MCP server safe to use?

Tomorrow Lives Engines scores 83 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the Tomorrow Lives Engines MCP server expose?

Tomorrow Lives Engines exposes 57 tools: art_schema, art_presets, art_materials, art_starter, art_check, and 52 more. Their descriptions and schemas cost roughly 13,767 tokens of context every time the server is loaded.

Does the Tomorrow Lives Engines MCP server require authentication?

Yes. Tomorrow Lives Engines asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

Is the Tomorrow Lives Engines MCP server still maintained?

Tomorrow Lives Engines is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.