Install Jentic One Beta

Connect the AnyHook API to your agent

Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the AnyHook API, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.

Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.

Step 1: Jentic One Host machine

# On the machine that will host your Jentic One instance:
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fanyhook.net%2Fanyhook" | sh

Step 2: Agent machine

# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fanyhook.net%2Fanyhook" | sh
jentic register       # connects your agent to your Jentic One instance

Jentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.

Capabilities

What an agent can do with AnyHook API.

Create webhook relay apps and configure their destinations

Connect Stripe or GitHub with a single provider key

Query the event delivery log across apps

Replay a single event or bulk-replay an app's failed deliveries

List the undelivered events for an app

GET STARTED

Start building with AnyHook API

Explore with Jentic One

View OpenAPI Document

Use Cases

Patterns agents use AnyHook API for, with concrete tasks.

★ AI agent wiring up webhook relays

An integration agent needs to start receiving a provider's webhooks without a developer configuring endpoints by hand. Through Jentic the agent searches for connecting a provider webhook, loads the connect operation with the key already injected, and registers the webhook so events begin flowing to a relay app. For providers beyond Stripe and GitHub, it creates an app first to obtain an inbound URL.

Call POST /api/v1/connect with a Stripe key, then GET /api/v1/events to confirm the first event arrived

Recovering missed webhooks

When a downstream service was down, an agent needs to find the deliveries that failed and send them again. AnyHook lists the undelivered events for an app and can re-deliver a single event or bulk-replay all failed ones, so the agent can recover a backlog without the provider resending. This closes the gap left by a temporary outage.

Call GET /api/v1/apps/{slug}/events/undelivered, then POST /api/v1/apps/{slug}/replay-failed to resend them

Inspecting webhook delivery

A support agent investigating a missing event queries the delivery log to see whether the webhook was received and how its delivery attempts went. AnyHook exposes a searchable event log and per-event replay, so the agent can confirm receipt, inspect the delivery history, and re-send a specific event if needed. This answers 'did the webhook arrive?' directly from the API.

Call GET /api/v1/events filtered to one app, then POST /api/v1/events/{id}/replay for the event that failed

Key Endpoints

16 endpoints — the anyhook api relays inbound webhooks from providers such as stripe, github, and shopify, giving each relay app an inbound url that receives and verifies events.

METHOD

PATH

DESCRIPTION

POST

/api/v1/apps

Create a new webhook relay app

GET

/api/v1/apps

List all relay apps

POST

/api/v1/connect

Connect Stripe or GitHub with a single key

GET

/api/v1/events

Query the event delivery log

POST

/api/v1/events/{id}/replay

Re-deliver a specific event

POST

/api/v1/apps/{slug}/replay-failed

Bulk-replay an app's failed events

POST

/api/v1/apps

Create a new webhook relay app

GET

/api/v1/apps

List all relay apps

POST

/api/v1/connect

Connect Stripe or GitHub with a single key

GET

/api/v1/events

Query the event delivery log

POST

/api/v1/events/{id}/replay

Re-deliver a specific event

POST

/api/v1/apps/{slug}/replay-failed

Bulk-replay an app's failed events

Why Jentic?

What agents get from Jentic-routed access to this vendor.

Setup

Wiring AnyHook by hand means creating relay apps, authenticating the management calls with your ahk_live bearer key, and leaving the ingress endpoint open because it verifies HMAC signatures itself. Through Jentic you install once, import AnyHook from the API Directory, store the key once, and your agent calls it.

Permission scoping

AnyHook puts the app slug in the management URL path (/api/v1/apps/{slug}/...), so a rule can pin your agent to one app and the operations you pick, such as reading its event log and replaying failures. You choose the operations it may call, so destructive ones like deleting an app or creating API keys stay out unless you add them.

Credential isolation

Your AnyHook bearer key is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context.

Intent-based discovery

Agents search Jentic by intent such as 'replay a failed webhook' or 'query the delivery log', and Jentic returns the matching AnyHook operation with its input schema so the agent calls the right endpoint without reading the reference docs.

FAQs

Specific to using AnyHook API through Jentic.

What authentication does the AnyHook API use?

The management API authenticates with a bearer key sent as Authorization: Bearer in the ahk_live format, per its OpenAPI spec. The ingress endpoint that receives provider webhooks needs no credential, because AnyHook verifies the HMAC signature on each inbound event instead. Through Jentic the bearer key is injected at call time for the management operations.

Can I replay a webhook that failed to deliver?

Yes. Call POST /api/v1/events/{id}/replay to re-deliver a single event, or POST /api/v1/apps/{slug}/replay-failed to bulk-replay every failed delivery for an app. You can first call GET /api/v1/apps/{slug}/events/undelivered to see what still needs sending.

What are the rate limits for the AnyHook API?

The OpenAPI spec does not state numeric rate limits. Throughput is governed by your plan and by how many relay apps and events your account processes. Check the AnyHook documentation for the current limits on your key before scripting large bulk replays.

Is there an AnyHook API MCP server?

You don't need an MCP server to give your agent the AnyHook API. Jentic connects it directly from the API Directory: import the API, store your bearer key once, and your agent calls operations such as GET /api/v1/events on demand without loading another server's tool definitions into its context.

Can I limit what my agent is allowed to do with the AnyHook API?

Yes. Write a rule that allows only the event-log read and the replay operations, so the agent can inspect deliveries and resend failed events but cannot delete an app or create new API keys, and every call it makes is logged. Destructive management operations stay out of the allowed set until you add them.

How do I query the webhook delivery log through Jentic?

Search Jentic for 'query webhook delivery log', load the GET /api/v1/events operation, and run it after your bearer key is stored. To run it on your own infrastructure, install Jentic One from its GitHub repo.

AnyHook API

AI ReadinessAI-Aware (B)66/100

See full scorecard

Official vendor OpenAPI document · agent-readyDeveloper ToolsMonitoring Observabilitybearer16 EndpointsREST

For Agents

Create webhook relay apps, connect providers like Stripe and GitHub, query the event delivery log, and replay failed or missed webhook deliveries.

Use for: Create a new webhook relay app, Connect a Stripe webhook with one key, Query the delivery log for recent events, Replay a specific failed event

Not supported: Does not send outbound email, SMS, or push notifications, and does not host your application. Use for relaying inbound provider webhooks and tracking their delivery only.

The AnyHook API relays inbound webhooks from providers such as Stripe, GitHub, and Shopify, giving each relay app an inbound URL that receives and verifies events. Its management surface creates and configures apps, connects a provider with a single key, queries a searchable event delivery log, and re-delivers events, either one at a time or by bulk-replaying an app's failed deliveries. It also lists undelivered events, rotates destination signing secrets, and manages API keys.

Jentic One on Github View OpenAPI Document

Show dimension breakdown

Foundational Compliance

Base layer of spec validity and structural soundness.

Grade: A+Signals: 4

98%

Lint Results

Aggregated quality score from linter diagnostics, weighted by severity.

100%

Resolution Completeness

Percentage of `$ref` references that resolve successfully.

100%

Specification Validity

Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).

75%

Structural Integrity

Structural correctness score based on schema issues using logarithmic dampening.

Developer Experience & Jentic Compatibility

Clarity, completeness, and ingestion readiness for developers and tooling.

Grade: BSignals: 4

Example Density

How richly the API is illustrated with examples.

100%

Example Validity

Percentage of examples that conform to their schemas.

53%

Response Coverage

Percentage of operations with complete response definitions (success, client error, server error).

100%

Tooling Readiness

Health of API ingestion, bundling, and resolution within Jentic pipelines.

AI-Readiness & Agent Experience

Semantic breadth, depth, and agent comprehension for AI systems.

Grade: DSignals: 4

38%

Description Coverage

Coverage of descriptions across API elements.

Error Standardization

Coverage of RFC 9457 Problem Details for error responses.

88%

OperationId Quality

Coverage, uniqueness, and casing consistency of operationIds for AI inference.

53%

Summary Coverage

Coverage of summaries across operations/tags/info.

Agent Usability

Functional utility, complexity comfort, and AI orchestration readiness.

Grade: A+Signals: 1

94%

Complexity Comfort

Agent comfort level based on API operational and structural complexity.

Security

Trust, risk posture, and security compliance.

Grade: B-Signals: 1

60%

Authentication Strength

Average quality of security schemes based on authentication method strength (weakest link for OAuth2).

AI Discoverability

Findability, semantic richness, and reasoning readiness.

Grade: ASignals: 1

87%

Descriptive Richness

Clarity and depth of descriptions across API elements.

Connect the AnyHook API to your agent

Capabilities

Start building with AnyHook API

Use Cases

Key Endpoints

Why Jentic?

Related APIs

FAQs

AnyHook API

Jentic AI Readiness Score

AnyHook API

Foundational Compliance

Lint Results

Resolution Completeness

Specification Validity

Structural Integrity

Developer Experience & Jentic Compatibility

Example Density

Example Validity

Response Coverage

Tooling Readiness

AI-Readiness & Agent Experience

Description Coverage

Error Standardization

OperationId Quality

Summary Coverage

Agent Usability

Complexity Comfort

Security

Authentication Strength

AI Discoverability

Descriptive Richness