Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Interfere 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%2Finterfere.com%2Finterfere" | shStep 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%2Finterfere.com%2Finterfere" | sh
jentic register # connects your agent to your Jentic One instanceJentic 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.
What an agent can do with Interfere API.
Register a release for a surface with its buildId, destination, and source using a build-time secret key
Sign a source-map upload session, upload maps one at a time or in batches of up to 512 KiB, and finalize with the bundler name
Check a release's source-map publication status for an environment without changing upload state
Resolve which surface and organization a build-time key belongs to via /v3/releases/config
GET STARTED
Attach a user identity, email, name, and traits to a session with a publishable surface key
Read a tenant's ARR and workspace tier, update one tenant, or patch up to 100 tenants at once
Patterns agents use Interfere API for, with concrete tasks.
★ Release and source-map checks from your agent through Jentic
A coding agent connected through Jentic finishes a deploy by registering the release with Interfere, then checks the source-map publication status for the production environment so stack traces will map back to source. If the maps are missing it can rerun the upload. The build-time secret key stays in your own Jentic One instance, not in the agent's context or the CI log.
Call POST /v3/releases with buildId, destination, and source for the build, then GET /v3/releases/{releaseSlug}/source-maps with environment 'production' and report whether the manifest is published
Signed source-map upload in CI
Source maps go up through a session: the sign call takes the list of files and returns the session expiry and inventory, the batch upload sends chunks atomically, and the finalize call records the bundler (webpack, turbopack, rollup, or tsc) and files. Finalized files are accepted durably while publication retries in the background.
Call POST /v3/releases/{releaseSlug}/source-maps/sign with the files list, PUT /v3/releases/{releaseSlug}/source-maps/batch with the chunks, then POST /v3/releases/{releaseSlug}/source-maps/finalize with bundler 'webpack' and the files
Weigh issues by customer value
Interfere can rank problems by who they affect. Workspace operations store each tenant's ARR in decimal major units with an ISO currency, plus a tier name that is created the first time it is assigned. A sync job can patch up to 100 tenants in one atomic call, and any unknown or foreign tenant rejects the whole batch.
Call PATCH /v3/workspaces/{workspaceSlug}/tenants/{endUserOrgId}/context with arr {amount: '48000', currency: 'USD'} and tier 'enterprise'
12 endpoints — the interfere api connects your builds and your app's sessions to interfere, an application monitoring service.
METHOD
PATH
DESCRIPTION
/v3/releases
Create a release
/v3/releases/{releaseSlug}/source-maps/sign
Sign a source-map upload session
/v3/releases/{releaseSlug}/source-maps/batch
Upload a source-map batch
/v3/releases/{releaseSlug}/source-maps/finalize
Finalize source maps
/v3/releases/{releaseSlug}/source-maps
Get source-map publication status
/v3/session/identify
Identify a session
/v3/workspaces/{workspaceSlug}/tenants/{endUserOrgId}/context
Update a tenant's ARR and tier
/v3/releases
Create a release
/v3/releases/{releaseSlug}/source-maps/sign
Sign a source-map upload session
/v3/releases/{releaseSlug}/source-maps/batch
Upload a source-map batch
/v3/releases/{releaseSlug}/source-maps/finalize
Finalize source maps
/v3/releases/{releaseSlug}/source-maps
Get source-map publication status
/v3/session/identify
Identify a session
/v3/workspaces/{workspaceSlug}/tenants/{endUserOrgId}/context
Update a tenant's ARR and tier
What agents get from Jentic-routed access to this vendor.
Setup
Wiring Interfere by hand means juggling a build-time secret key, a publishable key, and a Clerk session across different operations, and sequencing the sign, upload, and finalize steps for source maps. Through Jentic you install once, import Interfere from the API Directory, store each key once, and your agent calls it.
Permission scoping
Interfere puts the release slug and the workspace and tenant ids in the URL path (/v3/workspaces/{workspaceSlug}/tenants/{endUserOrgId}/context), so a rule can pin your agent to one workspace or one release and the operations you pick. You choose the operations it may call, so writes like tenant ARR updates or release registration are not included unless you add them.
Credential isolation
Your Interfere keys are stored once, encrypted, by your own Jentic One instance and injected at execution time. They never enter the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'upload source maps for a release' or 'update a tenant's ARR', and Jentic returns the matching Interfere operation with its input schema so the agent calls the right endpoint without browsing the reference docs.
Alternatives and complements available in the Jentic catalogue.
Specific to using Interfere API through Jentic.
Is there an Interfere MCP server?
You don't need an MCP server to give your agent Interfere. Jentic connects it directly from the API Directory: import it, store your key once, and your agent calls it. A coding agent finds the release or source-map operation it needs on demand instead of loading a server's tool list into its context.
Can I limit what my agent is allowed to do with the Interfere API?
Yes. For a deploy-check agent, write a rule that allows only GET /v3/releases/{releaseSlug}/source-maps and GET /v3/releases/config. It can confirm source maps were published for any release, but it cannot register releases, upload maps, or change tenant ARR, and every call it makes is logged.
What authentication does the Interfere API use?
Per its OpenAPI spec, it depends on the operation. Release and source-map operations take the surface's build-time secret key, either as a bearer token in the `Authorization` header or unwrapped in the `x-api-key` header. Session identify takes the publishable surface key in the `x-interfere-public-key` header or the `public_key` query parameter. Workspace tenant operations take a bearer Clerk session or delegated OAuth access token, and the spec notes they also accept API keys with explicit permission scopes. Through Jentic, each key is stored encrypted by your own Jentic One instance and injected into the calls that use it.
How large can an Interfere source-map batch be?
Per the spec, the complete JSON request to PUT /v3/releases/{releaseSlug}/source-maps/batch must not exceed 512 KiB. Larger sets can be split across several batches, or individual maps can be sent with PUT /v3/releases/{releaseSlug}/source-maps.
What are the rate limits for the Interfere API?
The OpenAPI spec does not specify rate limits; check https://interfere.com for current limits. The spec does ask clients to retry only when an operation's contract permits it and to keep the original idempotency key when they do.
How do I upload source maps with the Interfere API through Jentic?
Install Jentic One with `curl -fsSL https://raw.githubusercontent.com/jentic/jentic-one/main/tools/install.sh | sh`, import Interfere from the API Directory, and store your build-time key. Your agent searches for 'upload source maps for a release', gets the sign, batch upload, and finalize operations with their input schemas, and calls them in that order. To run it on your own infrastructure, install Jentic One from its GitHub repo.
For Agents
Register Interfere releases, run signed source-map uploads and check their publication status, identify user sessions, and read or update tenant ARR and tier.
Use for: Register release v2.4.1 with Interfere from my CI job, Upload the source maps for this build, Check whether the source maps for release v2.4.1 were published, Which surface does this build key belong to
Not supported: Does not handle reading error events, querying logs, or alerting through this spec. Use for registering releases, uploading source maps, identifying sessions, and setting tenant context only.
The Interfere API connects your builds and your app's sessions to Interfere, an application monitoring service. Build-time operations register a release for a surface and run a signed source-map upload session: sign the file inventory, upload maps singly or in batches, finalize them with the bundler used (webpack, turbopack, rollup, or tsc), and check publication status. At runtime, a publishable key attaches a user identity to a session, and workspace operations read and update each tenant's ARR and tier so issues can be weighed by customer value.
This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use.
Base layer of spec validity and structural soundness.
Aggregated quality score from linter diagnostics, weighted by severity.
Percentage of `$ref` references that resolve successfully.
Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).
Structural correctness score based on schema issues using logarithmic dampening.
Clarity, completeness, and ingestion readiness for developers and tooling.
How richly the API is illustrated with examples.
Percentage of examples that conform to their schemas.
Percentage of operations with complete response definitions (success, client error, server error).
Health of API ingestion, bundling, and resolution within Jentic pipelines.
Semantic breadth, depth, and agent comprehension for AI systems.
Coverage of descriptions across API elements.
Coverage of RFC 9457 Problem Details for error responses.
Coverage, uniqueness, and casing consistency of operationIds for AI inference.
Coverage of summaries across operations/tags/info.
Functional utility, complexity comfort, and AI orchestration readiness.
Agent comfort level based on API operational and structural complexity.
Trust, risk posture, and security compliance.
Average quality of security schemes based on authentication method strength (weakest link for OAuth2).
Findability, semantic richness, and reasoning readiness.
Clarity and depth of descriptions across API elements.
Score it yourself
Every API in the directory is allowlisted, so you can re-score it with no key required.
npx @jentic/api-scorecard-cli score <openapi-url>