Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Prosp Discovery 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%2Fprosp.cc%2Fprosp" | 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%2Fprosp.cc%2Fprosp" | 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 Prosp Discovery API.
Start a discovery from a saved icpId or inline criteria such as industries, locations, keywords, and company_sizes
Poll a discovery until its status is completed, failed, or exhausted, and read its result summary
List the companies one discovery found, or the de-duplicated prospect inbox across all discoveries
Run a semantic search over your prospects with the q parameter
GET STARTED
Fetch a prospect's detail and enrichments by its domain
Acknowledge delivered prospects by domain so they are not returned again
Save, update, and delete ideal customer profiles for repeat discoveries
Patterns agents use Prosp Discovery API for, with concrete tasks.
★ Agent-Run Prospect Discovery
An AI agent connected through Jentic takes a sales brief in plain language, starts a Prosp discovery with matching inline criteria, polls it until the status is terminal, and reads back the companies it found. It then acknowledges the prospects it has handed to the user, so the next run only surfaces companies the team has not seen.
Start a discovery with industries retail and locations Germany, poll it until status is completed, list its prospects, and acknowledge their domains
Saved ICP Re-Runs
Teams that target the same segment repeatedly save it once as an ICP with a name and criteria, then trigger discoveries by icpId. A body that mixes an icpId with inline criteria is rejected before any credit is debited, so a misconfigured request does not cost credits.
Create an ICP named 'EU Retail SMEs' with criteria for retail companies in the EU, then start a discovery with that icpId
Prospect Inbox Review
Sales reps work from one de-duplicated inbox of prospects gathered across every discovery. A rep or their assistant searches the inbox semantically with a q query, opens a company's detail by domain to read its enrichments, and acknowledges the ones they have actioned.
Search prospects with q 'refurbished electronics resellers', fetch the detail for the top domain, and acknowledge it
26 endpoints — the prosp discovery api finds companies that match an ideal customer profile and delivers them as prospects.
METHOD
PATH
DESCRIPTION
/api/v1/discoveries
Start a discovery
/api/v1/discoveries/{jobId}
Get a discovery's status and result
/api/v1/discoveries/{jobId}/prospects
List prospects one discovery found
/api/v1/prospects
List de-duplicated prospects
/api/v1/prospects/search
Semantic search over prospects
/api/v1/prospects/{domain}
Get prospect detail by domain
/api/v1/prospects/ack
Acknowledge prospect delivery
/api/v1/icps
Create a saved ICP
/api/v1/discoveries
Start a discovery
/api/v1/discoveries/{jobId}
Get a discovery's status and result
/api/v1/discoveries/{jobId}/prospects
List prospects one discovery found
/api/v1/prospects
List de-duplicated prospects
/api/v1/prospects/search
Semantic search over prospects
/api/v1/prospects/{domain}
Get prospect detail by domain
/api/v1/prospects/ack
Acknowledge prospect delivery
/api/v1/icps
Create a saved ICP
What agents get from Jentic-routed access to this vendor.
Setup
Wiring Prosp by hand means running the OAuth2 client credentials exchange against its token URL, refreshing the bearer token, adding an `X-Idempotency-Key` to credit-spending discovery requests, and polling jobs until they finish. Through Jentic you install once, import Prosp from the API Directory, store the client credentials once, and your agent calls it.
Permission scoping
Prosp puts the job id, ICP id, and prospect domain in the URL path (/api/v1/discoveries/{jobId}, /api/v1/icps/{icpId}, /api/v1/prospects/{domain}), so a rule can pin your agent to one discovery or one ICP and the operations you pick. You choose the operations it may call, so credit-spending discoveries and destructive ones like ICP deletion are not included unless you add them.
Credential isolation
Your Prosp client credentials are stored once, encrypted, by your own Jentic One instance, and the access token is injected at execution time. Neither enters the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'find companies matching my ideal customer profile' or 'list my new prospects', and Jentic returns the matching Prosp 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 Prosp Discovery API through Jentic.
What authentication does the Prosp Discovery API use?
The Prosp Discovery API uses OAuth2 with the client credentials grant, declared in its OpenAPI spec as the cognitoClientCredentials scheme with the mcp/execute scope. You exchange your client_id and client_secret for an access token at the token URL and send it as a bearer token in the Authorization header. The health probe operation needs no token. Through Jentic the client credentials are stored encrypted by your own Jentic One instance and the token is injected at call time.
How do Prosp discoveries use credits?
Starting a discovery costs credits, and the spec documents operations to read your current credit balance and your credit-transaction ledger. Sending an `X-Idempotency-Key` header makes a discovery request safe to retry, and a request that mixes a saved icpId with inline criteria is rejected with a 400 before any credit is debited.
What are the rate limits for the Prosp Discovery API?
The OpenAPI spec does not specify rate limits. Check https://prosp.cc for current limits on your account.
Is there a Prosp MCP server?
You don't need an MCP server to give your agent Prosp. Jentic connects the Prosp Discovery API directly from the API Directory: import it, store your client credentials once, and your agent calls it, with operations found on demand rather than loaded into its context up front.
Can I limit what my agent is allowed to do with the Prosp Discovery API?
Yes. For example, write a rule that allows only the prospect list, prospect search, and prospect detail operations, so the agent can read and search companies you have already discovered without starting credit-spending discoveries or deleting ICPs. Every call it makes is logged.
How do I start a prospect discovery with the Prosp Discovery API through Jentic?
Import the Prosp Discovery API from the Jentic API Directory, store your client credentials once, and have your agent search Jentic for 'find companies matching my ideal customer profile'. Jentic returns the create discovery operation with its input schema, which takes either an icpId or inline criteria; the agent then polls the discovery by jobId and reads its prospects. To run it on your own infrastructure, install Jentic One from its GitHub repo.
For Agents
Start prospect discoveries from a saved ideal customer profile or inline criteria, poll them to completion, and read, search, and acknowledge the companies found with Prosp.
Use for: Find small retail companies in the EU that match my ICP, Run my saved 'EU Retail SMEs' profile again, Check whether my latest discovery has finished, List all new prospects I haven't acknowledged yet
Not supported: Does not send outreach email, find personal contact emails, or manage deals. Use for discovering, searching, and acknowledging prospect companies only.
The Prosp Discovery API finds companies that match an ideal customer profile and delivers them as prospects. You start a discovery from a saved ICP or from inline criteria such as industries, locations, keywords, and company sizes, poll it until its status is completed, failed, or exhausted, and then read the companies it found. Prospects can be listed across all runs as a de-duplicated inbox, searched semantically, fetched by domain with their enrichments, and acknowledged so they are not delivered again. Discoveries spend credits, and an `X-Idempotency-Key` header makes a discovery request safe to retry.
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>