Eden MCP

Live

API KEY

CONTENT CREATION

Marketing

Eden MCP gives agents authenticated access to your content creation stack: find viral trends across 3M+ posts, analyze creators, and schedule posts in your voice.

  • Per-user credentials: each call uses the actual user's token, never a shared bot.
  • Encrypted per-tenant vault: AES-256, resolved at request time, never in LLM context.
  • Scoped before every call: pre-call scope check, 90-day SIEM-exportable audit chain.
Eden MCP
agent · Acme Q3
Run
What is going viral in the AI niche this week, and can you draft a carousel on it?
S
edenmcp_eden_search_social_content
102ms
Content agent
Top outlier: a LinkedIn carousel on agent memory, 4.2x above the creator's baseline. 2 more trending on X. Drafted a 7-slide carousel in your voice, saved to the queue.
Sources: 3 platforms, 7 days, outlier ranked
edenmcp
3 posts
18:29
Message Claude...

Tools your content agent reaches for on Eden, scoped per user.

CALL ANY TOOL
Run content creation end to end: search viral posts, analyze creators, generate carousels, and schedule or publish, each call scoped per user.
edenmcp_eden_search_social_content
Search social content
Search social posts across a creator, a curated list, your following, or the entire indexed corpus, with platform filters, follower tiers, and outlier-score thresholds.
Parameters
Name
Type
Required
Description
scope
object
Required
Search scope object. Set kind to 'creator', 'list', 'following', or 'global'. For 'creator': include creatorRef with platform and username. For 'list': include listRef with listId.
creatorTier
string
Optional
Follower-count band filter: micro (10k-100k), mid (100k-1M), macro (1M-10M), mega (10M+). Ignored on creator scope.
limit
integer
Optional
Maximum number of results to return (max 25).
minOutlierScore
number
Optional
Minimum outlier multiplier vs creator baseline. 2.0 = double typical; 3.0+ = real breakouts.
orderBy
string
Optional
Ranking method. Default is outlier (overperformers vs creator baseline).
platform
string
Optional
Optional platform filter on top of the scope.
query
string
Optional
Free-text search query (semantic for global/list/following scopes). Omit to get top posts ranked by outlier score.
since
string
Optional
Time window for the search. Default is lifetime.
workspaceId
string
Optional
Workspace ID to scope the search to. Optional if EDEN_WORKSPACE_ID is configured.
edenmcp_eden_analyze_creator
Analyze creator
edenmcp_eden_study_top_carousels
Study top carousels
edenmcp_eden_generate_carousel
Generate carousel
edenmcp_eden_create_scheduling_draft
Create draft post
edenmcp_eden_schedule_post
Schedule post
edenmcp_eden_publish_post_now
Publish now
edenmcp_eden_list_workspaces
List workspaces
Build your Agent
Same auth pattern across LangChain, OpenAI, Anthropic, and Google ADK.
Python · LlamaIndex
import { ScalekitClient } from "@scalekit-sdk/node";
import { createReactAgent } from "@langchain/langgraph/prebuilt";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

// Eden tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["edenmcp"], toolNames: [
    "edenmcp_eden_search_social_content",
    "edenmcp_eden_analyze_creator",
    "edenmcp_eden_create_scheduling_draft"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "What is going viral in my niche this week?" }] });
import OpenAI from "openai";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["edenmcp"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Analyze @lennysan's best posts and their patterns." }],
  tools,
});

// Execute the tool call with the user's vaulted Eden credential
await sk.tools.executeTool(res.choices[0].message.tool_calls[0], "user_123");
import Anthropic from "@anthropic-ai/sdk";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["edenmcp"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Draft next week's posts into the scheduling queue." }],
  tools,
});

// Tool call runs with the user's vaulted Eden credential
await sk.tools.executeTool(msg.content, "user_123");
import { Agent } from "@google/adk/agents";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["edenmcp"] }, pageSize: 100,
});

const agent = new Agent({
  name: "eden_content_agent",
  model: "gemini-2.5-pro",
  instruction: "Research trends and draft content for the signed-in user.",
  tools,
});

await agent.run("Study the top carousels in my niche for hook patterns.");
Try these prompts
Copy any prompt into your agent. Each maps directly to an Eden tool. Click to copy, paste into your agent, done.
Find what works
Copy the prompt
Copied
Show me the top outlier posts in my niche this week.
Copy the prompt
Copied
Analyze @lennysan's best posts and their content patterns.
Copy the prompt
Copied
Study the top-performing carousels for hook patterns.
Create in your voice
Copy the prompt
Copied
Generate a carousel about agent security in my voice.
Copy the prompt
Copied
Generate an image for tomorrow's launch post.
Copy the prompt
Copied
Draft 3 post ideas from this week's trends into the queue.
Schedule and publish
Copy the prompt
Copied
Schedule the carousel draft for Thursday at 9am.
Copy the prompt
Copied
List everything scheduled for next week.
Copy the prompt
Copied
Publish the MCP auth draft now.
SEE HOW AUTH WORKS
Your users connect once. Their Eden credentials stay vaulted, every call is scope-checked, and every action is logged.
1
Authorize
Your user connects
Eden MCP
once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access
Who:
user ‘A’
when:
Once per user
access:
Limited to user
2
Store
Their
Eden MCP
token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection
vault:
encrypted
scope:
per-user
tokens:
auto-refreshed
3
Resolve
When your agent calls a
Eden MCP
tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs
speed:
~40ms
check:
before every call
seen by:
nobody
4
Audit
Every
Eden MCP
tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it
history:
90 days
export:
SIEM-ready
logged:
every call
Test other agents
See the same per-user auth pattern across other content connectors.
SALES
Outbound prospecting agent
Build targeted prospect lists with Apollo, enrich with firmographic data, and draft personalised outreach. Runs on a schedule.
GTM
HubSpot to Slack updates agent
Watch HubSpot deal stage changes and post structured updates to the right Slack channel. Reps stop checking the CRM all day.
Why Scalekit
Secure your agent's access. Connectors ship in minutes
Other connector libraries treat auth as a demo afterthought. Scalekit starts with identity, scope enforcement, and audit. Connectors follow.
01.
Shared tokens break per-user analytics
A shared Eden key looks fine in a demo. In production every draft, schedule, and publish looks like one service account, and you cannot tell which creator's queue the agent touched. Scalekit resolves the credential of the actual user who triggered the agent, never a shared bot.
// shared key
audit → bot_service_account

// scalekit
audit → user_abc ✓
02.
Authentication is not authorization
03.
Multi-tenancy is architectural
04.
Eden today. Ten connectors tomorrow.
“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”
Venu Madhav Kattagoni
Head of Engineering / Von
FAQs
Frequently Asked Questions
Does the agent access Eden as the user or through a shared key?
As the user. Scalekit resolves the credential of the person who triggered the agent at request time, so every search, draft, and publish in your audit trail is attributed to a real user, not a shared service account.
Where is the Eden API key stored?
In an AES-256 encrypted vault with per-tenant namespacing. Keys are resolved at request time, never enter LLM context, and can be revoked from one dashboard.
Can I limit what the agent does in Eden?
Yes. Filter by tool name in listScopedTools to expose only what you want, for example research and drafting without publishing. Scalekit also enforces scope checks before every API call.
What happens when a user revokes access?
The credential is invalidated at the next tool call. The call fails closed, other users' connections are unaffected, and the revocation is logged in the audit chain.
Can the agent post to my social accounts without review?
Only if you let it. Exclude edenmcp_eden_publish_post_now and edenmcp_eden_schedule_post from listScopedTools and the agent can only create drafts in the queue for you to approve. Every publish that does happen is logged with the user's identity.
Start in your coding agent
Up and running in one command
Install the Scalekit skill in your editor of choice. Connector, auth, tools, prompt, all wired up
Claude Code REPL
/plugin marketplace add scalekit-inc/claude-code-authstack
/plugin install agentkit@scalekit-auth-stack
Cursor Code REPL
# ~/.cursor/mcp.json
{
""mcpServers"": {
""edenmcp"": {
""url"": ""https://mcp.scalekit.com/edenmcp"",
""headers"": { ""Authorization"": ""Bearer $SCALEKIT_TOKEN"" }
}
}
}
Codex Code REPL
# ~/.codex/config.toml
[mcp_servers.edenmcp]
url = ""https://mcp.scalekit.com/edenmcp""
auth_env = ""SCALEKIT_TOKEN""
Copilot Code REPL
# .vscode/mcp.json
{
""servers"": {
""edenmcp"": {
""url"": ""https://mcp.scalekit.com/edenmcp"",
""type"": ""http""
}
}
}