Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the COMPAMIR Data 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%2Fcompamir.com%2Fcompamir" | 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%2Fcompamir.com%2Fcompamir" | 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 COMPAMIR Data API.
Search structured news events filtered by genre, region, status, and date range
Fetch a single event's 5W1H summary together with its source links
List events flagged for reporting conflicts between sources
Read the controlled vocabulary and data-freshness metadata
Rotate or revoke the calling API key in place
GET STARTED
Patterns agents use COMPAMIR Data API for, with concrete tasks.
★ Agent News Monitoring
An AI agent connected through Jentic monitors a topic by searching COMPAMIR events filtered by genre, region, and date range, then fetching each event's 5W1H summary with its source links. Because sources are deduplicated into single events, the agent reviews one entry per story rather than many near-duplicate articles.
Search events for a region and genre since a start date, then fetch the 5W1H summary and source links for the top result
Reporting-Conflict Review
An analyst surfaces stories where sources disagree by listing COMPAMIR's conflict-flagged events. Each flagged event links back to its sources, so an agent can present the disagreement and the underlying reports for a human to judge, rather than asserting a single version.
List conflict-flagged events since yesterday and return each one's source links for review
Freshness-Aware Polling
A scheduled job reads COMPAMIR's metadata endpoint for data freshness before pulling events, so it only requests new data when the feed has advanced. The metadata also returns the controlled vocabulary, which an agent uses to build valid genre and region filters.
Read the metadata for data freshness and vocabulary, then search for events only if the feed has advanced since the last run
6 endpoints — the compamir data api is a read-only feed of structured news events in japanese and english, where multiple sources are deduplicated into single events.
METHOD
PATH
DESCRIPTION
/v1/events
Search events
/v1/events/{id}
Get an event by id
/v1/conflicts
List conflict-flagged events
/v1/meta
Read vocabulary and data freshness
/v1/keys/rotate
Rotate the API key
/v1/events
Search events
/v1/events/{id}
Get an event by id
/v1/conflicts
List conflict-flagged events
/v1/meta
Read vocabulary and data freshness
/v1/keys/rotate
Rotate the API key
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the COMPAMIR Data API by hand means managing a bearer key, building valid genre and region filters from the vocabulary metadata, and tracking the daily quota yourself. Through Jentic you install once, import the COMPAMIR Data API from the API Directory, store the key once, and your agent calls it.
Permission scoping
COMPAMIR puts the event id in the URL path (/v1/events/{id}), so a rule can allow your agent to read events, conflicts, and metadata and nothing else. You choose the operations it may call, so the key-rotation and key-revocation operations are not included unless you add them.
Credential isolation
Your COMPAMIR 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 'search structured news events' or 'list conflicting reports', and Jentic returns the matching COMPAMIR 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 COMPAMIR Data API through Jentic.
What authentication does the COMPAMIR Data API use?
The COMPAMIR Data API authenticates with a bearer API key in the Authorization header, per its OpenAPI spec. The key rotation and revocation operations authenticate with the key itself. Through Jentic the key is stored encrypted by your own Jentic One instance and injected at call time, so it never enters the agent's prompt, logs, or context.
Can I find news events where sources disagree with the COMPAMIR Data API?
Yes. A dedicated operation lists events flagged for reporting conflicts between sources, and each event links back to those sources. An agent can present both the disagreement and the underlying reports rather than committing to one version, which suits a human-in-the-loop review.
What are the rate limits for the COMPAMIR Data API?
The OpenAPI spec notes a daily quota that the key rotation and revocation operations do not consume, but does not state a fixed numeric request ceiling. Check https://api.compamir.com for the daily quota and limits that apply to your key.
Is there a COMPAMIR MCP server?
You don't need an MCP server to give your agent the COMPAMIR Data API. Jentic connects it directly from the API Directory: import it, store your key once, and your agent calls it. Operations are discovered on demand, so your agent's context stays lean instead of loading a separate server's tool definitions.
Can I limit what my agent is allowed to do with the COMPAMIR Data API?
Yes. Because this is a read-only data feed, you write a rule that allows only the event-search, event-fetch, conflict-list, and metadata operations, and leave the key-rotation and key-revocation operations out. The agent can then read news events but never change your credential, and every call it makes is logged.
How do I search news events through Jentic?
Import the COMPAMIR Data API from the Jentic API Directory, store your API key once, and have your agent search Jentic for 'search structured news events'. Jentic returns the events-search operation with its input schema so the agent sends the genre, region, and date filters and reads back the matching events. To run it on your own infrastructure, install Jentic One from its GitHub repo.
For Agents
Query a read-only feed of deduplicated, structured news events: search by genre, region, status, and date, fetch an event's 5W1H summary with source links, list reporting-conflict events, and read vocabulary and data-freshness metadata.
Use for: Search for recent news events in a given region, Get the 5W1H summary for a specific event, List events where the sources disagree, Find events in Japanese for a genre since last week
Not supported: Does not provide full article text, social media posts, or sentiment scores. Use for retrieving structured, deduplicated news events only.
The COMPAMIR Data API is a read-only feed of structured news events in Japanese and English, where multiple sources are deduplicated into single events. It searches events by genre, region, status, date range, and free text, returns a single event's AI-generated 5W1H summary with its source links, and lists events flagged for reporting conflicts between sources. A metadata endpoint reports the controlled vocabulary and data freshness, and key operations rotate or revoke the calling credential. The data is produced by automated processing rather than exhaustive human verification, and every event carries its source links.
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>