Eden So Eden MCP API
59
AI ReadinessFoundational (C+)59/100
Official vendor OpenAPI document · agent-readySocial MediaSocial Listeningoauth2, bearer4 EndpointsREST
For 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.
Use for: Research outlier posts about a topic on X and LinkedIn, Find breakout creators on TikTok and YouTube, Get analytics for a tracked social account, Create a board to collect research findings
Not supported: Does not run ad campaigns, host video, or send email. Use for social research, analytics, and scheduled publishing only.
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.
Install Jentic One Beta
Connect the Eden MCP API to your agent
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Eden MCP 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%2Feden.so%2Feden" | 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%2Feden.so%2Feden" | 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 Eden MCP API.
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
Patterns agents use Eden MCP API for, with concrete tasks.
★ 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.
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.
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.
Collect research references into a note, then schedule a post to publish at a set time
Key Endpoints
4 endpoints — 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.
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
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
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.
E
Eden MCP API
- Foundational (C+)59/100
87
Foundational Compliance58
Developer Experience & Jentic Compatibility35
AI-Readiness & Agent Experience94
Agent Usability75
Security78
AI DiscoverabilityPowered by JenticScoring Framework 1.0.0 | Scoring Engine 0.4.2
Show dimension breakdown
87
Foundational Compliance
Base layer of spec validity and structural soundness.
Grade: ASignals: 4
99%
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).
50%
Structural Integrity
Structural correctness score based on schema issues using logarithmic dampening.
58
Developer Experience & Jentic Compatibility
Clarity, completeness, and ingestion readiness for developers and tooling.
Grade: C+Signals: 4
0%
Example Density
How richly the API is illustrated with examples.
100%
Example Validity
Percentage of examples that conform to their schemas.
31%
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.
35
AI-Readiness & Agent Experience
Semantic breadth, depth, and agent comprehension for AI systems.
Grade: FSignals: 4
33%
Description Coverage
Coverage of descriptions across API elements.
0%
Error Standardization
Coverage of RFC 9457 Problem Details for error responses.
50%
OperationId Quality
Coverage, uniqueness, and casing consistency of operationIds for AI inference.
56%
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.
75
Security
Trust, risk posture, and security compliance.
Grade: A-Signals: 1
75%
Authentication Strength
Average quality of security schemes based on authentication method strength (weakest link for OAuth2).
78
AI Discoverability
Findability, semantic richness, and reasoning readiness.
Grade: A-Signals: 1
78%
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 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 isolation
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.
Intent-based discovery
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
Alternatives and complements available in the Jentic catalogue.
FAQs
Specific to using Eden MCP API through Jentic.
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.
GET STARTED