canonical: https://jentic.com/apis/eden.so/eden # Eden So Eden MCP API The Eden API gives agents outlier social research across X, LinkedIn, Instagram, TikTok, YouTube, and Substack, alongside private analytics, boards and notes, and post scheduling and publishing, all through a single JSON-RPC tools endpoint. Agents authenticate with OAuth 2.0 (PKCE, with dynamic client registration) or a personal access token and call the namespaced Eden tools exposed by that endpoint; a health check and OAuth discovery endpoints round out the surface. ## For AI agents Run outlier social research across X, LinkedIn, Instagram, TikTok, YouTube, and Substack, read private account analytics, manage boards and notes, and schedule or publish posts, all from one JSON-RPC endpoint with OAuth or a personal access token. ## Scope Does not run ad campaigns, host video, or send email. Use for social research, analytics, and scheduled publishing only. ## Capabilities - Research outlier posts and breakout creators across X, LinkedIn, Instagram, TikTok, YouTube, and Substack - Read private analytics on tracked social accounts - Create and update boards and notes in an Eden workspace - Schedule and publish social posts - Connect over a single JSON-RPC endpoint with OAuth 2.0 or a personal access token ## Use cases ### Agent-driven social research An agent researching a topic calls Eden to surface outlier posts and breakout creators across X, LinkedIn, Instagram, TikTok, YouTube, and Substack, then collects the standouts into a board. It discovers the research operations through Jentic by intent and calls Eden's tools without wiring the JSON-RPC transport by hand. Example prompt: Research outlier posts about a topic across X, LinkedIn, and TikTok, then save the top results to a new Eden board ### Cross-platform trend monitoring Keep a running read on how a topic or account is performing by combining Eden's outlier research with its private analytics. An agent can monitor a set of tracked accounts, pull their analytics, and flag posts that break out relative to their baseline. Example prompt: Pull analytics for a tracked account and list its posts whose engagement is outperforming the account's recent baseline ### Research-to-publish workflow Close the loop from research to posting by chaining Eden's research, notes, and scheduling operations. An agent can gather supporting references into notes, draft a post, and schedule it to publish at a chosen time from the same workspace. Example prompt: Collect research references into a note, then schedule a post to publish at a set time ## Key endpoints | Method | Path | Description | | --- | --- | --- | | POST | `/mcp` | Agent endpoint exposing Eden's tools over JSON-RPC | | GET | `/.well-known/oauth-protected-resource` | OAuth protected-resource metadata | | GET | `/.well-known/oauth-authorization-server` | OAuth authorization-server metadata | | GET | `/health` | Health check | ## Key resources - **Social research** — Surface outlier posts and creators across X, LinkedIn, Instagram, TikTok, YouTube, and Substack - **Analytics** — Read private analytics on tracked social accounts - **Boards and notes** — Create and organise boards and notes in a workspace - **Scheduling and publishing** — Schedule and publish social posts - **Connection** — JSON-RPC tools endpoint, health check, and OAuth discovery metadata ## AI readiness 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. - **Score:** 59 / 100 - **Maturity:** Foundational - **Dimensions:** - Foundational Compliance: 87 / 100 - Developer Experience & Jentic Compatibility: 58 / 100 - AI-Readiness & Agent Experience: 35 / 100 - Agent Usability: 94 / 100 - Security: 75 / 100 - AI Discoverability: 78 / 100 - **View full report:** https://jentic.com/apis/eden.so/eden/scorecard - **How the score is calculated:** https://docs.jentic.com/reference/api-readiness-framework/overview/ - **More about the dimensions:** https://docs.jentic.com/reference/api-readiness-framework/specification/#dimensional-model-overview ### Score it yourself Every API in the directory is allowlisted, so you can re-score it with no key required. - **Score your own API:** https://jentic.com/scorecard.md - **Scoring CLI agent skill:** https://github.com/jentic/jentic-api-scorecard/blob/main/skills/jentic-api-scorecard/SKILL.md ```sh npx @jentic/api-scorecard-cli score ``` ## Why Jentic - **Setup:** Wiring the Eden API by hand means registering an OAuth 2.0 client or minting a personal access token, then speaking JSON-RPC to its single tools endpoint and dispatching tool calls yourself. Through Jentic you install once, import the Eden API from the API Directory, store the credential once, and your agent calls it. - **Permission scoping:** You choose which Eden operations your agent can reach: add only the read-only social-research and analytics operations it needs, and leave scheduling, publishing, and workspace writes out. Eden names the operation inside the request rather than in the URL, so scoping is by operation, not by a path segment. - **Credential handling:** Your Eden credential 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. - **Discovery method:** Agents search Jentic by intent such as 'find outlier posts about a topic' or 'get analytics for an account', and Jentic returns the matching Eden operation with its input schema so the agent calls the right tool without browsing the reference docs. ## Related APIs - **Apify** — Scrapers and actors that collect social and web data - **Buffer** — Schedule and publish posts across social channels - **Mixpanel** — Product analytics for behaviour and funnels ## FAQ ### What authentication does the Eden API use? Per its OpenAPI spec, the main Eden agent endpoint authenticates with OAuth 2.0 (PKCE, with RFC 7591 dynamic client registration) or a personal access token sent as a bearer token; the health check and OAuth discovery endpoints are open. Through Jentic the credential is stored encrypted by your own Jentic One instance and injected at execution time, so it never enters the agent's context. ### Can I run social research across platforms with the Eden API? Yes. Eden's research operations surface outlier posts and creators across X, LinkedIn, Instagram, TikTok, YouTube, and Substack, and you can collect results into boards and read private analytics on tracked accounts. ### What are the rate limits for the Eden API? The OpenAPI spec does not state request rate limits, and OAuth access tokens expire after one hour and are refreshed with the refresh token. Check the Eden documentation at https://eden.so for current limits and token lifetimes. ### Is there an Eden MCP server? Yes, Eden offers a hosted MCP server, and you can also connect Eden through Jentic. Your credential is injected at call time by your self-hosted Jentic One instance instead of living in a connector config, your rules decide which Eden operations the agent may call, and adding the next API is an import rather than another connector to install and authorise. ### Can I limit what my agent is allowed to do with the Eden API? Yes. You decide which Eden operations the agent can reach: add only the read-only research and analytics operations and the agent cannot schedule, publish, or edit workspace data. Because Eden names the operation inside the request, scoping is by operation, and every call the agent makes is logged. ### How do I research social posts through Jentic? Search Jentic for 'find outlier posts about a topic', and it returns the matching Eden research operation with its input schema; your agent fills in the topic and platforms and calls it. To run it on your own infrastructure, install Jentic One from its GitHub repo.