emable
    Sign inGet started
    AI-native integration

    Build with Emable

    Discover a governed financial capability, inspect its evidence and price, connect it to an AI agent or app, run it with explicit approval, then reconcile usage, cost, result, and settlement.

    Read the complete Markdown guide Open public OpenAPI

    The product loop

    Discovery is always separate from execution. A listing or documentation result does not imply access, entitlement, or permission to spend credits.

    1. 1

      Discover

      Search capabilities or complete use cases by the outcome you need.

    2. 2

      Inspect

      Read evidence freshness, version, permissions, limitations, and supported surfaces.

    3. 3

      Quote

      Get the current maximum price before requesting execution approval.

    4. 4

      Run

      Use one explicit request, least-privilege access, and a fresh idempotency key.

    5. 5

      Reconcile

      Poll the shared run record and report status, result, and actual completed-step charges.

    Official machine-readable surfaces

    Documentation

    API llms.txtAPI llms-full.txtComplete Markdown guideVendor-neutral SKILL.md

    API contracts

    Public OpenAPI JSONPublic OpenAPI YAMLCapability manifestUse-case manifest

    Agent bundles

    Codex plugin bundleClaude plugin bundle

    A badge is described as official only after the relevant external directory approves it.

    Read-only MCP group

    Discovery and documentation tools

    docs:read

    These tools only read public documentation and manifests. They cannot access customer accounts, production inputs, prompts, raw results, or provider settlement data. Open a function to see when to use it, its scope, and its credit behavior.

    list_docs

    What it does

    Lists the public Emable guides, schemas, capability pages, and use-case pages.

    Use it when

    You need to see which documentation is available before choosing a specific page.

    Access

    docs:read; public metadata only

    Credit behavior

    Free; no reservation or charge

    search_docs

    What it does

    Searches public documentation titles and manifest summaries by a text query.

    Use it when

    You know the outcome or topic, but not the exact document or capability slug.

    Access

    docs:read; public metadata only

    Credit behavior

    Free; no reservation or charge

    get_doc

    What it does

    Returns one public documentation entry, its canonical URL, summary, kind, and related entries.

    Use it when

    You have a document slug and need the authoritative page to read or cite.

    Access

    docs:read; public metadata only

    Credit behavior

    Free; no reservation or charge

    list_capabilities

    What it does

    Lists governed capability contracts with outcome, provider, price, status, and execution surfaces.

    Use it when

    You need a reusable building block and want to search by outcome or provider.

    Access

    docs:read; public manifest only

    Credit behavior

    Free; no reservation or charge

    get_capability

    What it does

    Returns the full contract for one capability, including evidence freshness, permissions, limits, and exact maximum run cost.

    Use it when

    You are evaluating whether a capability is suitable and safe before integrating or running it.

    Access

    docs:read; public manifest only

    Credit behavior

    Free; no reservation or charge

    list_use_cases

    What it does

    Lists productized outcomes assembled from one or more governed capabilities.

    Use it when

    You want a complete business outcome rather than an individual capability.

    Access

    docs:read; public manifest only

    Credit behavior

    Free; no reservation or charge

    quote_use_case

    What it does

    Validates the supplied input and returns the current maximum price, step breakdown, approval requirement, and execution gate.

    Use it when

    Always before asking a user to approve or start a composed use-case run.

    Access

    docs:read; supplied quote input is validated, not executed

    Credit behavior

    Free; reserved_credits is always 0

    Compatibility MCP group

    Validator tools

    validator:read
    validator:run

    The original Validator tool names remain compatible. These tools operate within the authenticated caller's tenant and are distinct from public discovery. Open a function for its execution and charging boundary.

    list_audiences

    What it does

    Lists the caller's saved Validator audiences and their IDs.

    Use it when

    You need an audience_id before inspecting an audience or starting a validation.

    Access

    validator:read; tenant-scoped customer data

    Credit behavior

    Read-only metered call; no validation run started

    get_audience_details

    What it does

    Shows one saved audience profile and a preview of up to ten personas.

    Use it when

    You need to confirm that the selected people match the intended target group.

    Access

    validator:read; tenant-scoped customer data

    Credit behavior

    Read-only metered call; no validation run started

    create_audience

    What it does

    Creates a reusable audience from a name, description, market, and optional size.

    Use it when

    No existing audience represents the people you need to test.

    Access

    validator:run; writes tenant-scoped customer data

    Credit behavior

    Metered write; does not itself start a validation

    run_validation

    What it does

    Starts a 50-persona hypothesis validation against a saved audience and returns a simulation ID.

    Use it when

    The hypothesis, audience, market, stakes, and credit spend have been confirmed.

    Access

    validator:run; explicit execution

    Credit behavior

    Reserves the full run allowance, then settles actual run usage

    get_result

    What it does

    Polls one validation until it returns progress or a GO, CONDITIONAL, or NO-GO result.

    Use it when

    You have the simulation_id returned by run_validation.

    Access

    validator:read; tenant-scoped result

    Credit behavior

    Read-only metered call; no new validation run started

    list_validations

    What it does

    Lists recent validations with status, verdict, date, and dashboard link.

    Use it when

    You want run history, an earlier result, or to avoid repeating the same hypothesis.

    Access

    validator:read; tenant-scoped run history

    Credit behavior

    Read-only metered call; no new validation run started

    Application integration

    Core REST functions

    Use the public OpenAPI document for complete schemas. This reference explains the role and charging boundary of the main product-loop endpoints. Open an endpoint for its recommended usage and access rules.

    GET /v1/capabilities

    What it does

    Searches the runnable capability Store and returns available filters.

    Use it when

    Building Store search, catalog discovery, or an agent capability picker.

    Access

    Public manifest; private inventory is excluded

    Credit behavior

    Free

    GET /v1/capabilities/{slug}

    What it does

    Returns one capability contract and privacy-thresholded public statistics.

    Use it when

    Rendering a listing detail or checking price, evidence, trial, and permissions.

    Access

    Public manifest; statistics may be unavailable

    Credit behavior

    Free

    POST /v1/capabilities/{slug}/runs

    What it does

    Starts one entitled capability through the shared run and billing lifecycle.

    Use it when

    The manifest says runnable and the user has explicitly requested execution.

    Access

    capabilities:run plus entitlement and idempotency key

    Credit behavior

    Can reserve and charge credits; refusal is not charged

    GET /v1/use-cases

    What it does

    Searches productized use cases by outcome, country, provider, access, status, category, and maximum price.

    Use it when

    The user needs a complete outcome assembled from multiple capabilities.

    Access

    Public product manifest

    Credit behavior

    Free

    GET /v1/use-cases/{slug}

    What it does

    Returns one use case, its steps, dependencies, limits, price, and current execution blocker.

    Use it when

    Rendering a use-case detail or confirming whether execution is enabled.

    Access

    Public product manifest

    Credit behavior

    Free

    POST /v1/use-cases/{slug}/quote

    What it does

    Validates input and returns a one-hour maximum-cost quote with step prices.

    Use it when

    Before any composed execution approval.

    Access

    Public quote endpoint

    Credit behavior

    Free; reserves 0 credits

    POST /v1/use-cases/{slug}/runs

    What it does

    Starts a composed run only when the use case, adapter, platform, and commercial gate are enabled.

    Use it when

    After quote review and explicit user approval.

    Access

    use-cases:run plus all current gates

    Credit behavior

    Can reserve and settle step charges; currently gated for Market Entry

    GET /v1/runs and GET /v1/runs/{run_id}

    What it does

    Lists or reads the caller's shared run records across supported execution surfaces.

    Use it when

    Polling status, showing history, or reconciling actual completed-step charges.

    Access

    runs:read; tenant-scoped

    Credit behavior

    Free read

    /v1/saved-configurations

    What it does

    Saves, lists, deletes, and repeats private run inputs without exposing them in public analytics.

    Use it when

    A user wants to repeat the same governed configuration.

    Access

    runs:read or capabilities:run; tenant-scoped

    Credit behavior

    Saving is free; repeating a run can reserve and charge credits

    Connect your coding agent

    These commands register the hosted OAuth MCP endpoint. Approve only the feature groups required by your task.

    Codex

    codex mcp add emable --url https://api.emable.ai/mcp

    Claude Code

    claude mcp add --transport http emable https://api.emable.ai/mcp

    Gemini CLI

    gemini mcp add -s user -t http emable https://api.emable.ai/mcp

    VS Code

    code --add-mcp '{"name":"emable","type":"http","url":"https://api.emable.ai/mcp"}'

    Cursor, Claude Desktop, or a generic MCP client

    {
  "mcpServers": {
    "emable": {
      "type": "http",
      "url": "https://api.emable.ai/mcp"
    }
  }
}

    Quote before execution

    A quote validates the proposed input and returns the current ceiling without reserving credits. Market Entry execution remains closed until its commercial validation gate is met.

    TypeScript

    const quote = await fetch(
  "https://api.emable.ai/v1/use-cases/european-market-entry-pack/quote",
  { method: "POST", headers: { "Content-Type": "application/json" },
    body: JSON.stringify({ input }) }
).then(r => r.json());

    Python

    import httpx

response = httpx.post(
    "https://api.emable.ai/v1/use-cases/european-market-entry-pack/quote",
    json={"input": input}, timeout=30,
)
response.raise_for_status()
quote = response.json()

    Least privilege

    Documentation discovery never implies access to customer data or execution scopes.

    Predictable charging

    Quote first, reserve the maximum only when a run starts, settle successful steps once, and release the unused amount.

    Human control

    Treat awaiting_approval as a pause. No automatic outreach or named contact output proceeds without approval.

    Implementation prompt

    Use Emable to discover the governed capability or use case that best fits this outcome. Inspect evidence freshness, version, permissions, limitations, and maximum credit cost. Quote before execution. Do not spend credits, expose customer data, or perform outreach without explicit approval. Return citations and actual completed-step charges.