# AxonFlow

**Canonical:** https://apis.io/providers/axonflow/  
**Website:** https://docs.getaxonflow.com  
**APIs profiled:** 8

AxonFlow is a runtime governance platform for AI agents. It gives every agent a mandate, limits and a paper trail: deterministic policies evaluated before an agent acts, human approvals, PII redaction, AI usage budgets, tamper-evident audit logs and decision records exportable for frameworks such as the EU AI Act, RBI, SEBI and MAS FEAT. It ships an open-source Community Edition on GitHub, an Evaluation licence and a paid production program, runs in the customer's own environment, and integrates via Python, TypeScript, Go, Java and Rust SDKs and plugins for LangChain, LangGraph, CrewAI, LiteLLM, n8n, Claude Code, Cursor and others, plus an optional Fraud & Risk Add-on for payment agents.

## Kin Score — 71.3 / 100 (exemplar)

Scored 2026-10-09 under rubric 0.23.0.

| Facet | Score |
|---|---|
| Discoverability | 61.7 |
| Contract Quality | 61.8 |
| Contract Governance | 76.5 |
| Operational Transparency | 60.5 |
| Developer Ergonomics | 68.5 |
| Access Clarity | 84.2 |

Regulatory layer — **Horizontal (data, software, accessibility, platform)**: 29.4 (matched via fallback).

## Agent readiness — 41.4 (agent-native)

| Dimension | Value |
|---|---|
| Spec Presence | yes |
| Agentic Access | derived |
| Reversibility Documented | no |
| MCP Server | documented |
| Auth Clarity | bearer |
| Idempotency | verified |
| Error Semantics | verified |
| OpenAPI Examples | partial |
| Rate Limit Signal | verified |
| Event Surface Described | no |
| Agent Skills | derived |
| Well Known Catalog | no |
| Consent Identity | no |
| Agent Card | no |
| Dry Run Mode | no |
| Delegated Identity | no |
| Protected Resource Metadata | no |
| Dynamic Client Registration | no |
| Agentic Commerce | no |

## APIs (54)

- **AxonFlow Agents API** — Agent configuration management (MAP 0.8). **Enterprise only** — the `/api/v1/agents` route family is registered only in Enterprise builds with a database connection; Community r...
- **AxonFlow Assessments API** — FEAT Assessment lifecycle
- **AxonFlow Audit API** — Audit log search and retrieval
- **AxonFlow Audit Verification API** — Non-repudiation verification of the signed decision chain (#2722). Read-only endpoints that re-verify per-record Ed25519 signatures and the prev_hash linkage of a tenant's decis...
- **AxonFlow Bulk Operations API** — Import and export policies
- **AxonFlow Circuit Breaker API** — Emergency circuit breaker for AI operations (EU AI Act Article 14). Instantly halt AI operations with two-person deactivation requirement.
- **AxonFlow Community SaaS API** — Self-registration on the hosted Community SaaS deployment (`DEPLOYMENT_MODE=community-saas` only).
- **AxonFlow Compliance API** — The Compliance API from AxonFlow — 3 operation(s) for compliance.
- **AxonFlow Connectors API** — Connector marketplace
- **AxonFlow Cost Controls API** — Budget management and LLM usage tracking for cost optimization. Supports budgets at organization, team, agent, workflow, and user scopes. Provides usage summaries, breakdowns, a...
- **AxonFlow Cost Management API** — The Cost Management API from AxonFlow — 2 operation(s) for cost management.
- **AxonFlow Decision & Execution Replay API** — Decision & Execution Replay API for debugging, auditing, and compliance. Captures every step of workflow execution with full input/output snapshots and policy decisions.
- **AxonFlow Decision Mode API** — Synchronous policy decision endpoint (ADR-056). Called by an infrastructure gateway acting as a Policy Enforcement Point (PEP); AxonFlow returns a verdict (`allow` or `deny`) an...
- **AxonFlow Decisions & Overrides API** — Decision explainability (ADR-043) and session-scoped policy overrides (ADR-044). List recent governance decisions, explain a specific decision, and create/list/revoke time-boxed...
- **AxonFlow Dynamic Policies API** — Legacy policy management on `/api/v1/policies`. Reads, tests and simulation are served; writes answer `409 LEGACY_POLICY_WRITE_FROZEN` in v11 (see the `LegacyPolicyWriteFrozen` ...
- **AxonFlow EU AI Act API** — EU AI Act compliance endpoints for technical documentation export, conformity assessments (Article 43), and accuracy/bias tracking (Article 15). Enterprise feature for EU regula...
- **AxonFlow EU AI Act (Proxied) API** — EU AI Act compliance module (conformity assessments, accuracy monitoring, evidence exports). Served by the orchestrator and PROXIED through the agent (`/api/v1/euaiact/*`) per t...
- **AxonFlow Evidence Export API** — The Evidence Export API from AxonFlow — 2 operation(s) for evidence export.
- **AxonFlow Gateway Mode API** — Pre-check and audit for SDK-managed LLM calls
- **AxonFlow Health API** — Service health and readiness checks
- **AxonFlow HITL API** — Human-in-the-Loop decision queue (EU AI Act Article 14). Route high-risk AI decisions for human review before execution.
- **AxonFlow Kill Switch API** — Emergency system disable mechanism
- **AxonFlow LLM Providers API** — LLM provider management
- **AxonFlow MAP API** — The MAP API from AxonFlow — 1 operation(s) for map.
- **AxonFlow MCP Connectors API** — Model Context Protocol data connector operations
- **AxonFlow MCP Server API** — Streamable-HTTP MCP server (spec 2025-06-18) exposing AxonFlow governance as MCP tools (check_policy, check_output, audit_tool_call, list_policies, get_policy_stats, explain_dec...
- **AxonFlow Media Governance API** — Multimodal image governance for LLM requests. Analyzes images for PII (via OCR), content safety, face/biometric detection, and document classification. Community tier provides f...
- **AxonFlow Metrics API** — Performance monitoring and observability
- **AxonFlow Multi-Agent Planning API** — LLM-powered task decomposition and execution
- **AxonFlow OJK Compliance API** — OJK AI Governance + UU PDP compliance for Indonesian financial services. Audit export, retention/readiness checks, UU PDP Art. 46 breach-notification lifecycle, and a compliance...
- **AxonFlow OpenAI Compatible API** — OpenAI-compatible gateway endpoint (Issue #2351). Accepts standard OpenAI Chat Completions requests, runs AxonFlow policy checks, forwards to the upstream provider, records audi...
- **AxonFlow OTLP Ingest API** — OpenTelemetry OTLP/HTTP ingest for Claude Code (cowork) telemetry (#2832). **Enterprise only** — community builds mount the routes but return 501. Org/tenant identity always com...
- **AxonFlow Policies API** — Dynamic policy CRUD operations (Orchestrator)
- **AxonFlow Policy Simulation API** — The Policy Simulation API from AxonFlow — 3 operation(s) for policy simulation.
- **AxonFlow Processing API** — Main request processing pipeline
- **AxonFlow Proxy Mode API** — Full request interception and processing
- **AxonFlow RBI Compliance API** — RBI FREE-AI Framework compliance for Indian banking institutions. Enterprise feature providing AI System Registry, Model Validation, Incident Management, Kill Switch, Board Repo...
- **AxonFlow Registry API** — AI System Registry management
- **AxonFlow SEBI Compliance API** — SEBI AI/ML Guidelines compliance and DPDP Act 2023 audit exports. Enterprise feature for Indian financial services compliance.
- **AxonFlow Simulation API** — Policy simulation, impact reports, and conflict detection. **Evaluation tier and above.**
- …and 14 more, listed in full on the page.

## MCP servers (1)

- **AxonFlow MCP Server** — Built-in MCP server of the self-hosted AxonFlow agent (gateway). It is served by every AxonFlow deployment at /api/v1/mcp-server as a single Streamable-HTTP JSON-RPC 2.0 endpoin...

## Agentic access (1)

- **Axonflow Agentic Access** — 369 operations · 182 acting · 32 human-in-the-loop

## Security (2)

- **Axonflow Authentication** — apiKey/http · 6 schemes
- **Axonflow Domain Security** — TLSv1.3 · HSTS · DMARC

## Plans (1)

- **Axonflow Plans Pricing**

## Tags

Company, AI Governance, AI Agents, Policy Enforcement, Audit Logging, Compliance, MCP, Open Source

---

Profiled by [API Evangelist](https://apievangelist.com) and published on [APIs.io](https://apis.io/providers/axonflow/). Scores are computed from the provider's own public artifacts under a published rubric.
