Install Jentic One Beta

Connect the BirdSift API to your agent

Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the BirdSift 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%2Fbirdsift.com%2Fbirdsift" | 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%2Fbirdsift.com%2Fbirdsift" | 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 BirdSift API.

Run a bounded search for local businesses and save the results as leads

List the leads saved in a BirdSift workspace

Retrieve one saved lead by its id

Draft an outreach email for a saved lead

Check the workspace credit balance before running a search

GET STARTED

Start building with BirdSift API

Explore with Jentic One

View OpenAPI Document

Use Cases

Patterns agents use BirdSift API for, with concrete tasks.

★ Agent-run lead prospecting

An AI sales assistant builds a prospect list on demand. Through Jentic the agent runs a bounded local-business search, which saves the matches as leads, then lists them back for review. Each search spends workspace credits, so the agent can check the credit balance first and stop before exhausting it.

Check the credit balance, run a bounded search for 'dentists' in a target city, and list the leads it saved

Outreach drafting

A rep wants a first-pass outreach email for each prospect. The API drafts an outreach email for a saved lead, producing text for review rather than sending it, so a human stays in the loop before anything goes out. The draft is tied to the specific lead's saved details.

Draft an outreach email for a saved lead and return it for a human to review before sending

Credit-aware automation

A workflow stays inside its budget. Because searches and outreach drafts consume workspace credits, an agent reads the credit balance before each paid action and skips the work when the balance is too low. This keeps an unattended lead-gen loop from spending past its limit.

Read the workspace credit balance and only run a new search when enough credits remain

Key Endpoints

10 endpoints — the birdsift api runs bounded searches for local businesses, saves the results as leads, and drafts outreach emails for them.

METHOD

PATH

DESCRIPTION

POST

/v1/searches

Run a bounded search and save results

GET

/v1/leads

List saved leads

GET

/v1/leads/{id}

Get one saved lead

POST

/v1/leads/{id}/outreach-draft

Draft outreach email for a saved lead

GET

/v1/credits

Get credit balance

POST

/v1/searches

Run a bounded search and save results

GET

/v1/leads

List saved leads

GET

/v1/leads/{id}

Get one saved lead

POST

/v1/leads/{id}/outreach-draft

Draft outreach email for a saved lead

GET

/v1/credits

Get credit balance

Why Jentic?

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

Setup

Wiring the BirdSift API by hand means handling its bearer API key (and an OAuth 2.0 flow for scoped access) and tracking the workspace credits that searches and outreach drafts consume. Through Jentic you install once, import it from the API Directory, store the key once, and your agent calls it.

Permission scoping

The BirdSift API carries the lead id in the URL path (/v1/leads/{id}), so a rule can let your agent read saved leads and draft outreach for one lead while the credit-spending search operation is only included when you add it. You choose the operations the agent may call.

Credential isolation

Your BirdSift API key is held 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 'find local business leads' or 'draft an outreach email', and Jentic returns the matching BirdSift operation with its input schema so the agent calls the right endpoint without browsing the reference docs.

FAQs

Specific to using BirdSift API through Jentic.

What authentication does the BirdSift API use?

The BirdSift API authenticates with a workspace API key sent as a bearer token in the Authorization header per its OpenAPI spec, and it also declares an OAuth 2.0 authorization-code flow for scoped access. Through Jentic the key is injected at call time by your own Jentic One instance, so it never enters the agent's prompt or logs.

Can I draft outreach emails with the BirdSift API?

Yes. The outreach-draft operation produces an outreach email for a saved lead, using that lead's saved details. It drafts the email for review and does not send it, so a human can edit or approve the message before it goes out.

What are the rate limits for the BirdSift API?

The BirdSift API documents a limit of 60 requests per minute per API key in its OpenAPI spec. Searches and outreach drafts also consume workspace credits, so budget both the request rate and your remaining credit balance.

Is there a BirdSift MCP server?

Yes, the BirdSift API exposes an MCP endpoint for workspace-scoped access. You can also connect it directly through Jentic: your agent gets the full 10-endpoint surface without loading another server's tool definitions into its context, your key is injected at call time by your self-hosted instance instead of living in a config file, and your rules decide which operations the agent may call.

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

Yes. Write a rule that allows only the lead list and read operations, so the agent can browse saved leads but cannot spend credits by running a search or drafting outreach until you add those operations. Every call the agent makes is logged.

How do I find local business leads with the BirdSift API through Jentic?

Search Jentic for 'run a local business search' and it returns the search operation with its input schema; the agent passes the business type and location and reads back the saved leads, spending workspace credits. To run it on your own infrastructure, install Jentic One from its GitHub repo.

BirdSift API

AI ReadinessAI-Aware (B)64/100

See full scorecard

Official vendor OpenAPI document · agent-readyCRMContact Managementbearer, oauth210 EndpointsREST

For Agents

Find local-business leads, save and list them, check workspace credits, and draft outreach emails for a saved lead. Searches and drafts consume credits; drafts are not sent.

Use for: Find local businesses to add as leads, Run a bounded search for coffee shops in a city, List all leads saved in my workspace, Draft an outreach email for a saved lead

Not supported: Does not send emails, manage deal pipelines, or verify email deliverability. Use for local-business lead discovery and outreach drafting only.

The BirdSift API runs bounded searches for local businesses, saves the results as leads, and drafts outreach emails for them. An agent lists the leads saved in a workspace, reads one by id, and checks the workspace credit balance that searches and outreach drafts consume. The reference and OpenAPI document are served from the API itself, and outreach calls produce a draft for review rather than sending anything.

Jentic One on Github View OpenAPI Document

Show dimension breakdown

Foundational Compliance

Base layer of spec validity and structural soundness.

Grade: CSignals: 4

90%

Lint Results

Aggregated quality score from linter diagnostics, weighted by severity.

100%

Resolution Completeness

Percentage of `$ref` references that resolve successfully.

Specification Validity

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

35%

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: B-Signals: 4

Example Density

How richly the API is illustrated with examples.

100%

Example Validity

Percentage of examples that conform to their schemas.

40%

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: D+Signals: 4

48%

Description Coverage

Coverage of descriptions across API elements.

Error Standardization

Coverage of RFC 9457 Problem Details for error responses.

100%

OperationId Quality

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

48%

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: A-Signals: 1

75%

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

88%

Descriptive Richness

Clarity and depth of descriptions across API elements.

Connect the BirdSift API to your agent

Capabilities

Start building with BirdSift API

Use Cases

Key Endpoints

Why Jentic?

Related APIs

FAQs

BirdSift API

Jentic AI Readiness Score

BirdSift 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