Hive Civilization Xcalibur Membrane API

The xcalibur-membrane API from Hive Civilization — 5 operation(s) for xcalibur-membrane.

Documentation GitHub OpenAPI

Operations 5

Each operation below carries the questions people ask an LLM about it and the instructions they give an agent to run it. Generated by API Evangelist overlay

GET /v1/xcalibur/membrane/health Check MEMBRANE service liveness · Health #

Ask an LLM

“Is the MEMBRANE output-leak scorer alive?”

“How do I liveness-check MEMBRANE?”

Tell an agent

Check MEMBRANE health.

Ping the MEMBRANE liveness probe.

POST /v1/xcalibur/membrane/score Score an LLM output for sensitive-data leakage · Score #

Ask an LLM

“How can I tell whether a model's output leaked sensitive parts of the prompt?”

“What does a BLOCK, WARN or PASS decision from MEMBRANE mean?”

Tell an agent

Score output {output} against sensitive spans {spans}.

Rate leakage of {spans} in {output} under policy {policy} and return a signed receipt.

POST /v1/xcalibur/membrane/verify Verify a MEMBRANE scoring receipt · Verify #

Ask an LLM

“Is this MEMBRANE receipt's signature valid and its decision consistent with the thresholds?”

“How do I audit a leak-scoring receipt after the fact?”

Tell an agent

Verify MEMBRANE receipt {receipt}.

Check the signature and math on receipt {receipt}.

POST /v1/xcalibur/membrane/enforce Gate an LLM output, blocking it if it leaks · Enforce #

Ask an LLM

“Can I automatically block a model response that leaks sensitive prompt content?”

“What comes back when an output is blocked versus passed through the gate?”

Tell an agent

Enforce the leak gate on output {output} with sensitive spans {spans}.

Only let {output} through if it doesn't leak {spans} under policy {policy}.

GET /v1/xcalibur/membrane/canary-eval Run the adversarial canary leak benchmark · Canary Eval #

Ask an LLM

“How good is MEMBRANE at catching leaks versus passing clean outputs?”

“What sensitivity and specificity does the canary corpus report?”

Tell an agent

Run the MEMBRANE canary evaluation.

Benchmark leak detection against the built-in adversarial corpus.

Work with this as data

Every API here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for apis

7 MCP tools reach this

find_apisBrowse and filter every API in the catalog.
get_api_artifactsOne API's artifacts, grouped by type.
get_openapiThe primary OpenAPI for this API.
find_similar_apisAPIs that look like this one.
apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
resolveTurn a domain, URL or GitHub org into the provider it belongs to.
find_cohortsEvery scored population of providers in the catalog.

All 92 tools →

Call it yourself

curl for this page

This API

curl "https://apis.io/api/v1/apis/thehiveryiq-com:thehiveryiq-com-xcalibur-membrane-api"

All apis

curl "https://apis.io/api/v1/apis?limit=25"

Discovery needs no key. Ratings and market analysis are Pro.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

GitHub Google LinkedIn

A second provider on the same verified email joins the account you already have.

OpenAPI Specification

openapi: 3.2.0
info:
  title: HiveMorph v0.1 Xcalibur Membrane API
  description: 'Polymorphic agent runtime — single shape (Merchant), single supermodel (W2 MERCHANT). Three gates: NEED + YIELD + CLEAN-MONEY.'
  version: 0.1.0
tags:
- name: xcalibur-membrane
paths:
  /v1/xcalibur/membrane/health:
    get:
      tags:
      - xcalibur-membrane
      summary: Health
      description: Liveness probe for the MEMBRANE primitive.
      operationId: health_v1_xcalibur_membrane_health_get
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                additionalProperties: true
                type: object
                title: Response Health V1 Xcalibur Membrane Health Get
  /v1/xcalibur/membrane/score:
    post:
      tags:
      - xcalibur-membrane
      summary: Score
      description: 'Score an LLM output against sensitivity-labelled prompt spans.


        Returns the decision (BLOCK / WARN / PASS), IFS, and a signed receipt.'
      operationId: score_v1_xcalibur_membrane_score_post
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ScoreRequest'
        required: true
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                additionalProperties: true
                type: object
                title: Response Score V1 Xcalibur Membrane Score Post
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
  /v1/xcalibur/membrane/verify:
    post:
      tags:
      - xcalibur-membrane
      summary: Verify
      description: 'Verify a MEMBRANE receipt.


        Checks:

        - signature_ok: Ed25519 signature is valid against receipt body

        - math_ok: recorded decision is consistent with IFS and thresholds'
      operationId: verify_v1_xcalibur_membrane_verify_post
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/hivemorph__xcalibur__membrane_routes__VerifyRequest'
        required: true
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                additionalProperties: true
                type: object
                title: Response Verify V1 Xcalibur Membrane Verify Post
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
  /v1/xcalibur/membrane/enforce:
    post:
      tags:
      - xcalibur-membrane
      summary: Enforce
      description: 'Gate endpoint: runs scoring and either blocks or passes the output.


        - BLOCK → HTTP 403 with receipt

        - WARN / PASS → HTTP 200 with {"output": ..., "receipt": ...}'
      operationId: enforce_v1_xcalibur_membrane_enforce_post
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/EnforceRequest'
        required: true
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema: {}
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
  /v1/xcalibur/membrane/canary-eval:
    get:
      tags:
      - xcalibur-membrane
      summary: Canary Eval
      description: 'Run the built-in adversarial canary test corpus.


        Returns sensitivity (leak detection rate), specificity (clean pass rate),

        and per-case results. This is the seed of the MEMBRANE-EVAL-500 benchmark.'
      operationId: canary_eval_v1_xcalibur_membrane_canary_eval_get
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                additionalProperties: true
                type: object
                title: Response Canary Eval V1 Xcalibur Membrane Canary Eval Get
components:
  schemas:
    ValidationError:
      properties:
        loc:
          items:
            anyOf:
            - type: string
            - type: integer
          type: array
          title: Location
        msg:
          type: string
          title: Message
        type:
          type: string
          title: Error Type
        input:
          title: Input
        ctx:
          type: object
          title: Context
      type: object
      required:
      - loc
      - msg
      - type
      title: ValidationError
    PolicyModel:
      properties:
        tau_block:
          type: number
          maximum: 1.0
          minimum: 0.0
          title: Tau Block
          default: 0.18
        tau_warn:
          type: number
          maximum: 1.0
          minimum: 0.0
          title: Tau Warn
          default: 0.06
      type: object
      title: PolicyModel
    HTTPValidationError:
      properties:
        detail:
          items:
            $ref: '#/components/schemas/ValidationError'
          type: array
          title: Detail
      type: object
      title: HTTPValidationError
    hivemorph__xcalibur__membrane_routes__VerifyRequest:
      properties:
        receipt:
          additionalProperties: true
          type: object
          title: Receipt
      type: object
      required:
      - receipt
      title: VerifyRequest
    SpanModel:
      properties:
        text:
          type: string
          maxLength: 32000
          minLength: 1
          title: Text
        label:
          type: string
          maxLength: 64
          title: Label
          default: PUBLIC
      type: object
      required:
      - text
      title: SpanModel
    ScoreRequest:
      properties:
        spans:
          items:
            $ref: '#/components/schemas/SpanModel'
          type: array
          minItems: 1
          title: Spans
        output:
          type: string
          maxLength: 128000
          minLength: 1
          title: Output
        embedding_model_id:
          type: string
          title: Embedding Model Id
          default: tfidf-deterministic-v1
        policy:
          $ref: '#/components/schemas/PolicyModel'
      type: object
      required:
      - spans
      - output
      title: ScoreRequest
    EnforceRequest:
      properties:
        spans:
          items:
            $ref: '#/components/schemas/SpanModel'
          type: array
          minItems: 1
          title: Spans
        output:
          type: string
          maxLength: 128000
          minLength: 1
          title: Output
        embedding_model_id:
          type: string
          title: Embedding Model Id
          default: tfidf-deterministic-v1
        policy:
          $ref: '#/components/schemas/PolicyModel'
      type: object
      required:
      - spans
      - output
      title: EnforceRequest
x-provenance:
  method: harvested
  publisher: Hive Civilization
  source: https://receipts.thehiveryiq.com/openapi.json
  note: split by refine-openapis from the provider's own published document, verified by fetch (openapi/_original/*.fetch.json);
    stamped by stamp-openapi-provenance.py (roadmap#793)

Hive Civilization Xcalibur Membrane API

Operations 5

Documentation

Specifications

Other Resources

Work with this as data

MCP server

Tools for apis

Call it yourself

Get an API key

OpenAPI Specification