Official vendor OpenAPI document · agent-readyAnalyticsBusiness Intelligencebearer9 EndpointsREST
For Agents
Upload a redistricting plan as GeoJSON or a shapefile, score it with PlanScore's predictive model, and get back an index_url and a plan_url with the results. Re-score plans against newer model versions and list supported states and models.
Use for: I need to score a congressional district plan for partisan fairness, Upload this GeoJSON redistricting map to PlanScore, Re-score an existing plan with the newest model version, List all states PlanScore can score
Not supported: Does not handle voter registration, election results, or drawing district boundaries. Use for scoring uploaded electoral district plans only.
The PlanScore API scores electoral district plans for partisan fairness and returns a machine-readable index alongside a web page of graphs and maps. Small plans go up directly as a GeoJSON FeatureCollection of district polygons under 5MB, each optionally tagged with an Incumbent value of R, D, or O; larger files and shapefiles use a multistep flow that hands back pre-signed S3 upload fields and is finished with a call that adds incumbents, vote swings, and a model version. Existing plans can be re-scored against a newer predictive model, and temporary uploads and re-scores disappear within a week. The vendor marks the API as under development.
Install Jentic One Beta
Connect the PlanScore API to your agent
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the PlanScore 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.
1
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%2Fplanscore.org%2Fplanscore" | sh2
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%2Fplanscore.org%2Fplanscore" | 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.
Capabilities
What an agent can do with PlanScore API.
Score a GeoJSON district plan for partisan fairness by uploading a FeatureCollection of Polygon or MultiPolygon districts
Upload larger plans or shapefiles through pre-signed S3 upload fields, then finish with incumbents, vote_swings, and a model_version
Re-score an existing plan by its id against the latest predictive model or with an updated description
Run temporary scoring for drafts whose results disappear within a week
List the states and legislative bodies PlanScore can score, and the predictive model versions available
Attach library_metadata such as an authoritative_link or predecessor_link so a plan page cites its source
Use Cases
Patterns agents use PlanScore API for, with concrete tasks.
★ Agent-Driven Redistricting Analysis via Jentic
An AI agent supporting a redistricting researcher or journalist takes a proposed map, checks that the state is supported, and uploads it for scoring. Through Jentic the agent calls the PlanScore upload operation with the GeoJSON plan and returns the plan_url for the graphs and maps plus the index_url for machine-readable results, without the researcher wiring the bearer token or the S3 upload steps.
Call GET /states to confirm TX congress is supported, then upload a TX congressional GeoJSON plan with POST /upload and return its plan_url and index_url
Comparing Draft Redistricting Plans
Advocacy groups and legislative staff testing alternative maps submit each draft through the temporary upload so results expire within a week instead of joining the permanent library. Tagging each district's Incumbent property as R, D, or O improves the predictions, and each draft returns its own plan page for side-by-side review.
Upload three draft state house plans with POST /upload/temporary, each with Incumbent tags on every district, and collect the three plan_url values
Re-Scoring Enacted Plans with New Models
When PlanScore publishes a new predictive model, analysts re-run enacted plans to keep published figures current. The clone operation takes the existing plan id and an optional model_version and description, and plans shared with PlanScore are kept indefinitely, so the re-score sits next to the original.
List model versions with GET /model_versions, then call POST /clone with plan id 20210307T032912.752515089Z and the newest model_version and return the new plan_url
Key Endpoints
9 endpoints — the planscore api scores electoral district plans for partisan fairness and returns a machine-readable index alongside a web page of graphs and maps.
METHOD
PATH
DESCRIPTION
POST
/upload
Upload a GeoJSON district plan for scoring
GET
/upload
Get pre-signed S3 upload fields
POST
/uploaded
Complete a multistep upload and start scoring
POST
/clone
Re-score an existing plan
POST
/upload/temporary
Score a temporary plan
GET
/states
List supported states and legislative bodies
GET
/model_versions
List predictive model versions
POST
/upload
Upload a GeoJSON district plan for scoring
GET
/upload
Get pre-signed S3 upload fields
POST
/uploaded
Complete a multistep upload and start scoring
POST
/clone
Re-score an existing plan
POST
/upload/temporary
Score a temporary plan
GET
/states
List supported states and legislative bodies
GET
/model_versions
List predictive model versions
Jentic AI Readiness Score
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.
P
PlanScore API
- Foundational (C)54/100
90
Foundational Compliance69
Developer Experience & Jentic Compatibility28
AI-Readiness & Agent Experience94
Agent Usability60
Security75
AI DiscoverabilityPowered by JenticScoring Framework 1.0.0 | Scoring Engine 0.4.2
Show dimension breakdown
90
Foundational Compliance
Base layer of spec validity and structural soundness.
Grade: ASignals: 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).
60%
Structural Integrity
Structural correctness score based on schema issues using logarithmic dampening.
69
Developer Experience & Jentic Compatibility
Clarity, completeness, and ingestion readiness for developers and tooling.
Grade: B+Signals: 4
34%
Example Density
How richly the API is illustrated with examples.
100%
Example Validity
Percentage of examples that conform to their schemas.
42%
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.
28
AI-Readiness & Agent Experience
Semantic breadth, depth, and agent comprehension for AI systems.
Grade: FSignals: 4
58%
Description Coverage
Coverage of descriptions across API elements.
0%
Error Standardization
Coverage of RFC 9457 Problem Details for error responses.
0%
OperationId Quality
Coverage, uniqueness, and casing consistency of operationIds for AI inference.
53%
Summary Coverage
Coverage of summaries across operations/tags/info.
94
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.
60
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).
75
AI Discoverability
Findability, semantic richness, and reasoning readiness.
Grade: A-Signals: 1
75%
Descriptive Richness
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>Why Jentic?
What agents get from Jentic-routed access to this vendor.
Setup
Wiring PlanScore by hand means requesting a bearer token by email, choosing between direct GeoJSON upload and the pre-signed S3 multistep flow, and posting the completion call with incumbents and model version. Through Jentic you install once, import PlanScore from the API Directory, store the token once, and your agent scores plans.
Permission scoping
PlanScore carries the plan id in the request body rather than the URL path, so rules bound which operations your agent may call, not which plan. You choose the operations it may call, so permanent uploads and re-scores are not included unless you add them.
Credential isolation
Your PlanScore bearer token 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 'score a redistricting plan' or 're-score a district map', and Jentic returns the matching PlanScore operation with its input schema so the agent calls the right endpoint without browsing the reference docs.
Related APIs
Alternatives and complements available in the Jentic catalogue.
FAQs
Specific to using PlanScore API through Jentic.
What authentication does the PlanScore API use?
The PlanScore API uses bearer authentication per its OpenAPI spec: send your token in an Authorization: Bearer header. Tokens are issued on request by emailing info@planscore.org. The spec applies the bearer scheme at the top level, and describes the browser upload fields operation as intended for direct browser use. Through Jentic the token is stored encrypted on your own instance and injected at call time.
Is there a PlanScore MCP server?
You don't need an MCP server to give your agent PlanScore. Jentic connects it directly from the API Directory: import PlanScore, store your bearer token once, and your agent can upload and score district plans straight away. Operations are discovered on demand, so no extra server's tool definitions sit in your agent's context.
Can I limit what my agent is allowed to do with the PlanScore API?
Yes. Write a rule that allows only the temporary upload, temporary clone, and states operations, so the agent can score drafts whose results expire within a week but cannot add plans to the permanent library, and every call it makes is logged.
How do I upload a plan larger than 5MB to PlanScore?
Use the multistep flow. Call GET /upload for a pre-signed S3 URL and form fields, post the file to S3, then call POST /uploaded with the redirect from S3 plus an optional description, incumbents list, vote_swings, and model_version to start scoring. The same flow handles shapefiles.
What are the rate limits for the PlanScore API?
The PlanScore OpenAPI spec does not specify rate limits, and the vendor marks the API as under development. Ask info@planscore.org about usage limits when you request a token.
How do I score a district plan with the PlanScore API through Jentic?
Search Jentic for an intent like 'score a redistricting plan', import PlanScore, and store your bearer token once. Your agent then calls POST /upload with a GeoJSON FeatureCollection of districts and reads the plan_url and index_url from the response. To run it on your own infrastructure, install Jentic One from its GitHub repo.
GET STARTED