lemma-tan.vercel.app
Lemma is an IDE for human-agent mathematical reasoning.
First seen 2026-11-05 · Last seen 2026-11-05 · Source: webmcp.com
Answer 9 · Act 13 · Transact 0 · Score: Not yet scored
Tool inspector
create_step
Append a step to an active branch when the expected branch revision is current. When its known prerequisites already exist, provide their IDs in depends_on_step_ids to create directed prerequisite dependencies atomically with the new step. Each prerequisite must belong to the same objective; duplicate prerequisites are rejected. This mutation is idempotent for the supplied idempotency_key.
Input schema
| Property | Type | Required | Description |
|---|---|---|---|
branch_id |
string | yes | A UUID that identifies a persisted Lemma resource. |
title |
string | yes | — |
body_markdown |
string | yes | Markdown with inline TeX delimited by $...$ and display TeX delimited by $$...$$. |
depends_on_step_ids |
array | no | UUIDs of existing prerequisite steps that the new step depends on. Each dependency is created atomically with the new step. |
expected_branch_revision |
integer | yes | A positive optimistic-concurrency revision. |
idempotency_key |
string | yes | A caller-generated key that makes a mutation retry safe. |
summary |
— | no | — |
concepts |
array | no | — |
theorem_tags |
array | no | — |
status |
string | no | — |
supersedes_step_id |
— | no | — |
author_type |
string | yes | — |
author_agent_name |
string | no | — |
Raw JSON schema
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"type": "object",
"properties": {
"branch_id": {
"type": "string",
"format": "uuid",
"pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
"description": "A UUID that identifies a persisted Lemma resource."
},
"title": {
"type": "string",
"minLength": 1,
"maxLength": 240
},
"body_markdown": {
"type": "string",
"minLength": 1,
"maxLength": 200000,
"description": "Markdown with inline TeX delimited by $...$ and display TeX delimited by $$...$$."
},
"depends_on_step_ids": {
"default": [],
"description": "UUIDs of existing prerequisite steps that the new step depends on. Each dependency is created atomically with the new step.",
"maxItems": 64,
"type": "array",
"items": {
"type": "string",
"format": "uuid",
"pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
"description": "A UUID that identifies a persisted Lemma resource."
}
},
"expected_branch_revision": {
"type": "integer",
"exclusiveMinimum": 0,
"maximum": 9007199254740991,
"description": "A positive optimistic-concurrency revision."
},
"idempotency_key": {
"type": "string",
"minLength": 8,
"maxLength": 200,
"description": "A caller-generated key that makes a mutation retry safe."
},
"summary": {
"anyOf": [
{
"type": "string",
"maxLength": 2000
},
{
"type": "null"
}
]
},
"concepts": {
"default": [],
"maxItems": 64,
"type": "array",
"items": {
"type": "string",
"minLength": 1,
"maxLength": 160
}
},
"theorem_tags": {
"default": [],
"maxItems": 64,
"type": "array",
"items": {
"type": "string",
"minLength": 1,
"maxLength": 160
}
},
"status": {
"default": "active",
"type": "string",
"enum": [
"draft",
"active"
]
},
"supersedes_step_id": {
"anyOf": [
{
"type": "string",
"format": "uuid",
"pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
"description": "A UUID that identifies a persisted Lemma resource."
},
{
"type": "null"
}
]
},
"author_type": {
"type": "string",
"enum": [
"human",
"agent"
]
},
"author_agent_name": {
"type": "string",
"minLength": 1,
"maxLength": 160
}
},
"required": [
"branch_id",
"title",
"body_markdown",
"expected_branch_revision",
"idempotency_key",
"author_type"
],
"additionalProperties": false
}
Similar websites
pocketgull.app
Pocket Gull is a real-time clinical AI consult engine powered by Google Gemini. Features 10D multi-paradigm strategy, FHIR R4 export & 3D spatial anatomy.
webmcp-six-lac.vercel.app
AI Navigation Layer: Model Context Protocol (MCP) Semantic DOM integration for intelligent, safe, and observable web navigation.
ghqsandbox.net
Interactive math and physics tools an AI agent can drive directly through WebMCP.
app.formative.com
Formative classroom assessment and learning platform