Install Jentic One Beta

Connect the ProxyPics API to your agent

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

Order a property photo request for an address from a template token, or with your own task list on the crowdsource or direct platform

Approve submitted photos, or reject them with a reason such as blurry_photo, wrong_direction, or incorrect_property

Extend a photo request's expires_at, duplicate an existing order, or cancel one that is no longer needed

Create appraisal requests of type AutomatedValuationRequest, EvaluationRequest, or AppraisalFormRequest and approve the result

GET STARTED

Start building with ProxyPics API

Explore with Jentic One

View OpenAPI Document

Use Cases

Patterns agents use ProxyPics API for, with concrete tasks.

★ Agent-managed property photo orders

An AI agent working a lending or insurance queue can order a ProxyPics photo request for each property address, watch its status, and review the result. When photos come back it approves them, or rejects them with a reason from the API's list such as blurry_photo or people_in_photo so the collector can retake them, keeping the file moving without a human opening the web app.

Create a photo request for address 12 Main St, Springfield, IL with a template_token and loan_number LN-4471, then approve it once its status shows completed

Automated valuation and BPO ordering

Lenders and servicers order a value opinion alongside photos. The appraisal-requests operations take an address and a type of AutomatedValuationRequest for an AVM, EvaluationRequest for a simple BPO, or AppraisalFormRequest for a BPO with adjustments, with an optional report_provider of ca or quantarium, then return the request for review and approval.

Create an appraisal request with type AutomatedValuationRequest and report_provider quantarium for 40 Oak Ave, Austin, TX

Order event webhooks

Instead of polling, an integration registers a webhook URL with a get or post method and optional basic-auth username and password. ProxyPics then sends events such as PhotoRequestAssigned, AppointmentScheduled, and PhotoRequestReportGenerated, and the company settings decide which events trigger a webhook or an email.

Create a webhook with url https://hooks.example.com/proxypics and method post, then list webhooks to confirm it was registered

Key Endpoints

25 endpoints — the proxypics api orders on-site property photo requests, which a crowdsourced data collector or the property owner fulfils, and lets you approve or reject the submitted photos.

METHOD

PATH

DESCRIPTION

POST

/photo-requests

Create a photo request

GET

/photo-requests/{id}

Show a photo request

PUT

/photo-requests/{id}/approve

Approve a photo request

PUT

/photo-requests/{id}/reject

Reject a photo request with a reason

PUT

/photo-requests/{id}/extend

Extend a photo request expiry

POST

/appraisal-requests

Create an appraisal request

POST

/webhooks

Create a webhook

POST

/photo-requests

Create a photo request

GET

/photo-requests/{id}

Show a photo request

PUT

/photo-requests/{id}/approve

Approve a photo request

PUT

/photo-requests/{id}/reject

Reject a photo request with a reason

PUT

/photo-requests/{id}/extend

Extend a photo request expiry

POST

/appraisal-requests

Create an appraisal request

POST

/webhooks

Create a webhook

Why Jentic?

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

Setup

Wiring ProxyPics by hand means choosing between its x-api-key header and api_key query parameter, switching between the live and sandbox hosts, and building the photo request body with either a template_token or a task list. Through Jentic you install once, import ProxyPics from the API Directory, store the key once, and your agent calls it.

Permission scoping

ProxyPics puts the photo request id in the URL path (/photo-requests/{id}/...), so a rule can pin your agent to one order and the operations you pick. You choose the operations it may call, so ones like creating paid orders, cancelling requests, or creating API keys are not included unless you add them.

Credential isolation

Your ProxyPics API 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 'order property photos' or 'reject inspection photos', and Jentic returns the matching ProxyPics operation with its input schema so the agent calls the right endpoint without reading the reference docs.

FAQs

Specific to using ProxyPics API through Jentic.

What authentication does the ProxyPics API use?

The ProxyPics API authenticates with an API key, which its OpenAPI spec lets you send either in the x-api-key header or as the api_key query parameter. You generate keys on the Integrations tab of your ProxyPics profile. Through Jentic the key is stored once and injected at call time, so it never appears in your agent's prompt or logs.

Can I reject photos and ask for a retake with the ProxyPics API?

Yes. PUT /photo-requests/{id}/reject takes a required reason from a set including blurry_photo, wrong_direction, incorrect_property, people_in_photo, and property_not_visible, plus an optional clarification for the collector. PUT /photo-requests/{id}/approve accepts the photos instead.

What are the rate limits for the ProxyPics API?

The OpenAPI spec does not specify rate limits for the ProxyPics API. Check the ProxyPics API reference at https://app.swaggerhub.com/apis-docs/proxypics/proxypics-api/1.0.0 for current limits before bulk ordering.

How do I order a property photo request with the ProxyPics API through Jentic?

Search Jentic for 'order property photos', which returns POST /photo-requests with its input schema, then send the required address along with a template_token, or a photo_request_platform and tasks list if you have no template. To run it on your own infrastructure, install Jentic One from its GitHub repo.

Is there a sandbox for testing the ProxyPics API?

Yes. The spec lists a sandbox server on the sandbox.proxypics.com host, a separate ProxyPics instance where requests are never completed by real collectors and you can simulate submission, approval, and rejection. It needs its own account and API key from sandbox-app.proxypics.com.

Is there a ProxyPics MCP server?

You don't need an MCP server to give your agent the ProxyPics API. Jentic connects it directly from the API Directory: import it, store your credential once, and your agent calls it, with operations found on demand instead of a full tool list loaded into context.

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

Yes. Write a rule that allows only listing and showing photo requests plus the approve and reject operations, so the agent can review submitted photos but cannot place new paid orders, create API keys, or change company settings, and every call it makes is logged.

ProxyPics API

AI ReadinessFoundational (D+)50/100

See full scorecard

Community OpenAPI document · agent-readyProductivityTask ManagementapiKey25 EndpointsREST

Know of an official OpenAPI document? Contribute it →

For Agents

Order property photo requests by address, extend or cancel them, and approve or reject the submitted photos with a reason. Also creates AVM and BPO appraisal requests and manages webhooks and API keys.

Use for: I need to order exterior photos of 12 Main St for a loan file, Reject the photos on request 5521 because the property is not visible, Extend the photo request deadline by two days, Check whether the photo request for this address has been completed

Not supported: Does not handle property listing search, title records, or full licensed appraisals by itself. Use for ordering and reviewing on-site property photo and valuation requests only.

The ProxyPics API orders on-site property photo requests, which a crowdsourced data collector or the property owner fulfils, and lets you approve or reject the submitted photos. It also creates appraisal requests such as automated valuations and BPOs, exchanges messages on an order, and registers webhooks for events like assignment, completion, and report generation. A separate sandbox instance at sandbox.proxypics.com lets you simulate photo submission and review before ordering live.

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).

21%

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.

50%

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: FSignals: 4

65%

Description Coverage

Coverage of descriptions across API elements.

Error Standardization

Coverage of RFC 9457 Problem Details for error responses.

OperationId Quality

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

57%

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: FSignals: 1

33%

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: BSignals: 1

63%

Descriptive Richness

Clarity and depth of descriptions across API elements.

Connect the ProxyPics API to your agent

Capabilities

Start building with ProxyPics API

Use Cases

Key Endpoints

Why Jentic?

Related APIs

FAQs

ProxyPics API

Jentic AI Readiness Score

ProxyPics 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