Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the meertrack 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%2Fmeertrack.com%2Fmeertrack" | 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%2Fmeertrack.com%2Fmeertrack" | 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 meertrack API.
List the workspace's tracked competitors filtered by active status or id, with expand=full for social links and page URLs
Read one competitor's overview with per-section item lists for its 12 overview sections
Pull the activity feed filtered by competitor_id, section such as pricing or job-listings, and change_type of added, updated, or removed within a from and to window
Resolve one or many activity items by row id for the full detail behind a change
GET STARTED
Page through weekly digests by competitor and date range, or fetch the latest digest for every competitor
Check the caller's auth context and workspace with the me route before running a report
Patterns agents use meertrack API for, with concrete tasks.
★ Agent-written competitor briefings through Jentic
A product marketing agent can write a weekly competitor briefing through Jentic. It pulls the activity feed for the past week filtered to sections such as pricing, messaging, and job-listings, resolves the most important items for detail, and combines them with each competitor's latest digest, all read-only, so it cannot change what the workspace tracks.
Call the activity feed with section pricing and messaging, change_type updated, and from set to seven days ago, resolve the returned items, then fetch the latest digests and write a one-page briefing
Pricing and packaging watch
Sales and pricing teams want to know the moment a rival changes its pricing page. Filtering the activity feed to the pricing section within a date window returns every added, updated, or removed pricing item, so a team can review exactly what changed and when.
Pull activity with section pricing and from set to yesterday, and post each changed pricing item with its competitor name to the sales channel
Hiring signal tracking
Job listings reveal where a competitor is investing. Filtering activity to the job-listings section with change_type added shows new roles over a period, and the competitor overview lists current job listings alongside other tracked sections.
Pull activity for competitor_id of Acme with section job-listings, change_type added, and from set to the start of the quarter, then group the roles by team
9 endpoints — the meertrack api reads the competitor intelligence a meertrack workspace collects: each tracked competitor's profile, social links, and tracked page urls, plus a change feed across sections such as blog posts, press posts, job listings, ads, pricing, case studies, linkedin and x posts, reviews, youtube videos, events, messaging, claimed metrics, logos, and sitemap urls.
METHOD
PATH
DESCRIPTION
/competitors
List tracked competitors
/competitors/{id}
Get a competitor overview
/activity
Cross-competitor change feed
/activity/items
Resolve multiple activity items
/digests/latest
Latest digest per competitor
/digests
List weekly digests
/competitors
List tracked competitors
/competitors/{id}
Get a competitor overview
/activity
Cross-competitor change feed
/activity/items
Resolve multiple activity items
/digests/latest
Latest digest per competitor
/digests
List weekly digests
What agents get from Jentic-routed access to this vendor.
Setup
Wiring meertrack by hand means handling its bearer key, strict query validation that rejects unknown parameters, cursor pagination, and per-instance rate limits with jittered backoff. Through Jentic you install once, import meertrack from the API Directory, store the key once, and your agent calls it.
Permission scoping
meertrack puts competitor, digest, and activity row ids in the URL path (/competitors/{id}, /digests/{id}), so a rule can bound your agent to the read operations you pick and, on those routes, to specific records. All operations are reads, so the choice is about which data the agent sees, such as digests only rather than the full activity feed.
Credential isolation
Your meertrack 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 'see competitor pricing changes' or 'get the latest competitor digest', and Jentic returns the matching meertrack 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 meertrack API through Jentic.
What authentication does the meertrack API use?
The meertrack API authenticates with a bearer token per its OpenAPI spec: every request sends Authorization: Bearer with an mt_live_ key. Workspace admins mint keys in the app under Settings, the plaintext is shown once, and a lost key can only be revoked and re-issued. Through Jentic the key is stored encrypted on your own instance and injected at call time.
Is there a meertrack MCP server?
You don't need an MCP server to give your agent meertrack. Jentic connects it directly from the API Directory: import it, store your credential once, and your agent calls it. Operations are discovered on demand, which keeps another server's tool definitions out of your agent's context.
Can I limit what my agent is allowed to do with the meertrack API?
Yes. Every meertrack operation is a read, so the useful limit is which data the agent sees. For example, write a rule that allows only GET /digests/latest, so a briefing agent can read each competitor's latest digest but not the raw activity feed or item detail. Every call it makes is logged.
What are the rate limits for the meertrack API?
The spec states a limit of 60 requests per minute per workspace, enforced per serverless instance, so X-RateLimit-Remaining is not monotonic across requests. Treat a rate-limited response with X-RateLimit-Reset as the backoff signal and add jitter.
How do I get only recent changes instead of the whole roster?
Pass from, and optionally to, on GET /activity. With a window you get adds, updates, and removals in that period only. Omit both and you get the complete all-time roster, including items that existed when tracking began, so change_type=added then covers nearly everything.
How do I pull competitor changes with meertrack through Jentic?
Search Jentic for an intent like 'see what competitors changed this week', import the meertrack API, and store your key once. Your agent then calls GET /activity with a from date and the sections it cares about, and GET /activity/items to resolve the details. To run it on your own infrastructure, install Jentic One from its GitHub repo.
For Agents
Read tracked competitors, pull a feed of their added, updated, or removed pricing, jobs, ads, posts, and messaging changes over a date window, and fetch weekly competitor digests from a meertrack workspace. Read-only.
Use for: What pricing changes did our competitors make this week, List all new job listings posted by Acme in the last 30 days, Get the latest weekly digest for every competitor, Find all ads competitors removed since Monday
Not supported: Does not handle adding or configuring tracked competitors, sending alerts, or web scraping on demand. Use for reading meertrack competitor profiles, change activity, and digests only.
The meertrack API reads the competitor intelligence a meertrack workspace collects: each tracked competitor's profile, social links, and tracked page URLs, plus a change feed across sections such as blog posts, press posts, job listings, ads, pricing, case studies, LinkedIn and X posts, reviews, YouTube videos, events, messaging, claimed metrics, logos, and sitemap URLs. The activity feed returns additions, updates, and removals within a from and to window, or the full current roster when no window is given, and individual items can be resolved by row id. Weekly digests summarise each competitor, with a shortcut to the latest digest per competitor.
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>