FeedOracle Technologies

FeedOracle Technologies Agent Guard API

Runtime agent security & governance. 20 tools across 4 layers: pre-execution, payload security, governance, post-execution. Agent state machine with automatic escalation.

Documentation GitHub OpenAPI

Operations 2

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

POST /guard/mcp Call AgentGuard tools over JSON-RPC at /guard/mcp · AgentGuard MCP Server (20 tools) #

Ask an LLM

“Can I call policy_preflight or output_safety_scan through the /guard/mcp JSON-RPC endpoint?”

“Which tools does the AgentGuard server at /guard/mcp list, and which need a bearer token?”

Tell an agent

Send JSON-RPC method {method} with params {params} to the /guard/mcp AgentGuard server.

List the tools on the /guard/mcp endpoint using request id {id}.

POST /guard-oracle/mcp/ Use the guard-oracle runtime security MCP server · AgentGuard MCP endpoint (20 security tools) #

Ask an LLM

“Where can I connect an MCP client for runtime security like emergency kill and scope checking?”

“What agent states does the guard-oracle endpoint track, such as suspended or killed?”

Tell an agent

Connect to the guard-oracle MCP endpoint and list its security tools.

Use the guard-oracle runtime security server to scan my agent's output for safety issues.

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/tooloracle-io:tooloracle-io-agentguard-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: FeedOracle Compliance Evidence Agent Guard API
  version: 8.4.1+truthrepair.r1
  description: 'FeedOracle Compliance Evidence Infrastructure — 44 MCP servers, 590+ evidence tools across 17 data sources. DORA, MiCA, AMLR and CSRD compliance evidence APIs. ES256K-signed responses, blockchain-anchored. Canonical metrics: https://feedoracle.io/data/feedoracle-metrics.json.'
  contact:
    email: support@feedoracle.io
    url: https://feedoracle.io/contact.html
  license:
    name: Proprietary
  termsOfService: https://feedoracle.io/terms.html
servers:
- url: https://api.feedoracle.io
  description: Production
security: []
tags:
- name: AgentGuard
  description: 'Runtime agent security & governance. 20 tools across 4 layers: pre-execution, payload security, governance, post-execution. Agent state machine with automatic escalation.'
paths:
  /guard/mcp:
    post:
      tags:
      - AgentGuard
      summary: AgentGuard MCP Server (20 tools)
      description: 'JSON-RPC 2.0 MCP endpoint. Methods: initialize, tools/list, tools/call. Tools include policy_preflight, tool_risk_score, output_safety_scan, emergency_kill, tool_manifest_verify, and 15 more. Bearer token required for non-public tools.'
      operationId: agentguardMcp
      requestBody:
        content:
          application/json:
            schema:
              type: object
              properties:
                jsonrpc:
                  type: string
                  example: '2.0'
                id:
                  type: integer
                  example: 1
                method:
                  type: string
                  enum:
                  - initialize
                  - tools/list
                  - tools/call
                params:
                  type: object
      responses:
        '200':
          description: MCP JSON-RPC response
        '401':
          description: Bearer token required
      security:
      - bearerAuth: []
  /guard-oracle/mcp/:
    post:
      tags:
      - AgentGuard
      summary: AgentGuard MCP endpoint (20 security tools)
      description: 'Runtime security for AI agent workflows. Policy preflight, output safety scan, audit logging, emergency kill, rate limiting, scope checking. Agent states: active/monitoring/approval_required/suspended/killed.'
      operationId: agentGuardMcp
      responses:
        '200':
          description: MCP JSON-RPC response
components:
  securitySchemes:
    ApiKeyAuth:
      type: apiKey
      in: header
      name: X-API-Key
      description: Required for v1 data endpoints. Get at /pricing.html
    BearerAuth:
      type: http
      scheme: bearer
      bearerFormat: JWT
      description: OAuth 2.0 Bearer token from POST /mcp/token
    bearerAuth:
      type: http
      scheme: bearer
      description: FeedOracle OAuth 2.1 Bearer token. Obtain via /mcp/register (Dynamic Client Registration, RFC 7591).
x-nomos-trust-chain:
  model: S0-S10
  manifest: https://agentnomos.com/.well-known/nomos-capabilities.json
x-provenance:
  method: harvested
  publisher: FeedOracle Technologies
  source: https://feedoracle.io/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)