Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Comunicate.eu 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%2Fcomunicate.eu%2Fcomunicate" | 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%2Fcomunicate.eu%2Fcomunicate" | 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 Comunicate.eu API.
Search the publisher sites by niche, campaign type, authority, and price with GET /partner/catalog, and read per-site terms and accepted campaign types with GET /partner/catalog/{siteId}
Create an article from HTML with title, contentHtml, focusKeyword, and seoTitle via POST /partner/articles, or import Word and other documents with POST /partner/articles/import
Order a written article by topic (tema), campaignType, and word count (cuvinte) with POST /partner/redactare and track the order through statuses like NOUA and LIVRATA
Run an SEO analysis with GET /partner/articles/{articleId}/seo and check campaign-type fit with GET /partner/articles/{articleId}/potrivire before submitting
GET STARTED
Request publication of one article on one or more sites by siteIds and campaignType with POST /partner/publications, optionally scheduled with scheduledFor
Check owned packages, remaining credits, and money balance with GET /partner/balance before booking
Plan a budget in lei by niche and city with the open GET /public/plan route, no key needed
Patterns agents use Comunicate.eu API for, with concrete tasks.
★ Advertorial booking agent through Jentic
A marketing agent can run an advertorial campaign end to end on Comunicate.eu. Through Jentic it finds each operation by intent: it searches GET /partner/catalog for sites in the right niche, creates the article with POST /partner/articles, checks GET /partner/articles/{articleId}/potrivire against the campaign type, confirms credit with GET /partner/balance, and books with POST /partner/publications. The bk_live_ key is injected at call time and never sits in the agent's context.
Call POST /partner/publications with articleId 'art_123', two siteIds from GET /partner/catalog, and a campaignType listed in each site's acceptedCampaigns, after confirming GET /partner/balance shows enough available credit
Pre-submission quality checks
Rejected articles cost a publication cycle. GET /partner/articles/{articleId}/seo returns a score, findings, and an issues list with a code, severity, and message for each problem, while GET /partner/articles/{articleId}/potrivire answers a different question: whether the text is the article that was ordered for the campaign type, since an SEO-perfect text that carries links fails a brand-mention campaign.
Call GET /partner/articles/art_123/seo and GET /partner/articles/art_123/potrivire with the campaignType the client ordered, then list every issue with its code and severity
Importing drafts from documents and Drive
Clients often send articles as Word files or a shared Drive folder. POST /partner/articles/import accepts .docx, .odt, .rtf, .html, and other formats, while GET /partner/articles/drive lists a folder shared with anyone with the link so the agent can pick the right documents before POST /partner/articles/drive imports them, with one result entry per file.
Call GET /partner/articles/drive with link set to the shared folder URL, choose the final draft files, then call POST /partner/articles/drive with link and fisiere listing those files
Campaign reporting for clients
Agencies report back to clients per campaign. GET /partner/campaigns/{campaignId} returns a campaign with its articles and publications, GET /partner/reports/summary returns a period summary defaulting to the last 30 days, and GET /partner/reports/publications returns publications row by row for client reporting.
Call GET /partner/reports/summary with from '2026-10-01' and to '2026-10-31', then GET /partner/reports/publications, and summarise the published placements for the client
39 endpoints — the comunicate.
METHOD
PATH
DESCRIPTION
/partner/catalog
List publications
/partner/articles
Create an article from HTML
/partner/redactare
Order an article
/partner/articles/{articleId}/potrivire
Check campaign-type match
/partner/publications
Request publication
/partner/publications/{publicationId}
One publication
/partner/balance
Available balance
/public/plan
Budget plan
/partner/catalog
List publications
/partner/articles
Create an article from HTML
/partner/redactare
Order an article
/partner/articles/{articleId}/potrivire
Check campaign-type match
/partner/publications
Request publication
/partner/publications/{publicationId}
One publication
/partner/balance
Available balance
/public/plan
Budget plan
What agents get from Jentic-routed access to this vendor.
Setup
Wiring Comunicate.eu by hand means choosing between a bk_live_ bearer key and an OAuth 2.1 PKCE flow, learning which routes are open, and handling 409 payment-choice retries yourself. Through Jentic you install once, import the Comunicate.eu API from the API Directory, store the key once, and your agent calls it.
Permission scoping
Comunicate.eu puts the article, campaign, order, and publication ids in the URL path, so a rule can hold your agent to one article (/partner/articles/{articleId}/...) or one campaign. You choose the operations it may call, so spending or destructive ones like publication requests or campaign deletion are not included unless you add them.
Credential isolation
Your Comunicate.eu 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 'publish an advertorial on news sites' or 'check an article against campaign rules', and Jentic returns the matching Comunicate.eu 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 Comunicate.eu API through Jentic.
Is there a Comunicate.eu MCP server?
Yes - per its OpenAPI spec, Comunicate.eu offers an MCP server. You can also connect the Comunicate.eu API directly through Jentic: your agent gets the full 39-endpoint surface from the spec without loading another server's tool definitions into its context, your key is injected at call time by your self-hosted instance instead of living in an MCP config, and your rules decide which operations the agent may call.
What authentication does the Comunicate.eu API use?
Per its OpenAPI spec, the /partner routes accept an API key from Integrations sent as a bearer token (Authorization: Bearer bk_live_...), or an OAuth 2.1 access token from the authorization code flow with PKCE and scopes such as CATALOG_READ, ARTICLES_WRITE, and PUBLICATIONS_WRITE. The /public routes are open and need no key, and writing anything requires a key. Through Jentic, the key is stored encrypted by your own Jentic One instance and injected at call time.
How do I pay for a publication through the API?
POST /partner/publications pays from an owned package or the money balance. When several owned packages cover the same site, the request is rejected with 409 and a list of options, and you retry with packageTypeId. Check GET /partner/balance first; written-article orders through POST /partner/redactare are paid from the money balance, not from credits.
Can I limit what my agent is allowed to do with the Comunicate.eu API?
Yes. For example, write a rule that allows GET /partner/catalog, POST /partner/articles, and the GET /partner/articles/{articleId}/seo and /potrivire checks, but not POST /partner/publications or POST /partner/redactare. The agent can then draft and check advertorials without spending credit or money, and every call it makes is logged.
What are the rate limits for the Comunicate.eu API?
The OpenAPI spec does not specify rate limits for the /partner routes, and it states the /public routes carry no rate-limit headers to negotiate. Check https://comunicate.eu for current limits.
How do I request publication of an article through Jentic?
Search Jentic for 'publish an advertorial on news sites', load the post_publications operation, and call POST /partner/publications with articleId, siteIds, and campaignType, which are all required. To run it on your own infrastructure, install Jentic One from its GitHub repo.
Can I see what an advertorial costs without an account?
Yes. The open routes need no key: GET /public/statistici-piata returns market statistics including price per campaign type, GET /public/plan returns publication packages for a budget in lei by niche and city, and GET /public/niches lists niches with publication counts and average authority.
For Agents
Search publisher sites, create or order advertorial articles, check them against campaign-type rules, request publication on chosen sites, and track campaigns, balance, and publication status.
Use for: Find news sites in the auto niche that accept press releases under a set price, I need to publish this press release on three Romanian news sites, Check whether my article passes the brand-mention campaign rules before I submit it, Order a 600-word advertorial about our new store opening
Not supported: Does not host your own blog, run paid search or display ads, or send email newsletters. Use for booking and tracking advertorial and press release placements on publisher sites only.
The Comunicate.eu API books advertorials and press releases on a network of publisher websites in Romania, Italy, and beyond. It searches the publisher list by niche, campaign type, authority, and price, creates articles from HTML or imported Word and Drive documents, orders professionally written articles, and requests publication of an article on chosen sites, paid from owned packages or the money balance. Before submitting, an agent can run an SEO analysis on an article and check whether it matches the ordered campaign type. Campaigns, balance, publication reports, and a live domain audit round out the surface, and a set of open public routes returns niches, budget plans, and market statistics without a key.
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>