For Agents
Send a task or question to Cedric, an AI employee in your Slack, Telegram, or Discord workspace, get his reply, upload files for his tools, and call his tools over JSON-RPC.
Use for: Ask Cedric to summarise yesterday's meeting notes, I want to hand a task to my Cedric workspace from a script, Upload a recording so Cedric can work with it, List all the tools Cedric can use in my workspace
Not supported: Does not handle Slack, Telegram, or Discord administration, workspace billing, or raw model completions. Use for running Cedric turns, uploading files for his tools, and calling his connected tools only.
The Cedric API runs turns with Cedric, an AI employee that works in Slack, Telegram, and Discord, from scripts, tests, automations, and other agents. A chat call sends a message, optionally continuing a session, and returns Cedric's reply as JSON once the whole turn completes, with his memory, connected tools, scheduling, and credits applied as on any other surface. A files endpoint uploads up to five local files per request for his tools to use, and a JSON-RPC 2.0 endpoint over Streamable HTTP exposes the tools his workspace has connected. Every caller acts as the key owner in their workspace, and the key's mode decides whether sends and writes wait for a person's approval or run immediately.
Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Cedric 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%2Fmeet-cedric.com%2Fmeet-cedric" | 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%2Fmeet-cedric.com%2Fmeet-cedric" | 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 Cedric API.
Run one full Cedric turn from code with POST /api/v1/chat and receive his reply as JSON
Continue a conversation by passing a session key, or start fresh with session set to new
Upload up to five local files of up to 100 MB each and get file ids his tools accept
Call the tools Cedric's workspace has connected through JSON-RPC 2.0 messages such as tools/list and tools/call
Hand Cedric a whole task through the ask_cedric tool, with standard-mode keys holding sends and writes for approval
Patterns agents use Cedric API for, with concrete tasks.
★ Your agent delegating work to Cedric
A developer's own agent can hand Cedric a task that touches the tools Cedric is already connected to in the workspace. Through Jentic the agent searches for 'ask Cedric to do a task', loads the runChatTurn operation, and posts a message to POST /api/v1/chat, with the cedric_sk_ key injected by Jentic. Under a standard-mode key any send or write Cedric proposes waits for a person to approve it in Slack, Telegram, or Discord.
POST /api/v1/chat with message 'Summarise the action items from today's standup and post them to #team for approval' and session 'new', then return Cedric's reply
Feeding files to Cedric
Tool calls are JSON and cannot carry a video or a large document, so files go through POST /api/v1/files as multipart form-data: up to 5 files per request, 100 MB each. The response lists each file's id for Cedric's tools to use, any file that could not be stored appears in refused with the reason, and files are kept for 30 days, a year once shared, or permanently with keep.
POST /api/v1/files with a meeting recording in files and path 'meetings/2026-11', then POST /api/v1/chat asking Cedric to transcribe the file by its returned id
Tests and automations against a live workspace
Teams that build on Cedric can script checks against real behaviour. POST /api/v1/chat runs the same turn as every other surface, so a test can send a fixed prompt and assert on the reply, while POST /api/v1/mcp with a tools/list message shows exactly which tools the workspace offers that caller, since the list grows as apps are connected.
POST /api/v1/mcp with jsonrpc '2.0', id 1, and method 'tools/list', then POST /api/v1/chat with a test prompt and check the reply mentions a connected tool
3 endpoints — the cedric api runs turns with cedric, an ai employee that works in slack, telegram, and discord, from scripts, tests, automations, and other agents.
METHOD
PATH
DESCRIPTION
/api/v1/chat
Run one turn and get the reply
/api/v1/files
Upload local files
/api/v1/mcp
Send one JSON-RPC tool message
/api/v1/chat
Run one turn and get the reply
/api/v1/files
Upload local files
/api/v1/mcp
Send one JSON-RPC tool message
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>What agents get from Jentic-routed access to this vendor.
Setup
Wiring Cedric by hand means creating a cedric_sk_ key in his Settings, choosing standard or direct mode, building multipart uploads for files, and framing JSON-RPC 2.0 messages for his tool endpoint. Through Jentic you install once, import Cedric from the API Directory, store the key once, and your agent calls it.
Permission scoping
Cedric exposes three POST paths and carries the message, files, or JSON-RPC method in the request body, so rules bound which operations your agent may call, not what it asks Cedric to do. You choose the operations it may call, so file uploads and direct tool calls are not included unless you add them.
Credential isolation
Your Cedric API 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 'ask Cedric to do a task' or 'upload a file for Cedric', and Jentic returns the matching Cedric operation with its input schema so the agent calls the right endpoint without reading the reference.
Alternatives and complements available in the Jentic catalogue.
Specific to using Cedric API through Jentic.
What authentication does the Cedric API use?
The OpenAPI spec declares two schemes. apiKey is an HTTP bearer key in the form Authorization: Bearer cedric_sk_..., created in Cedric's Settings and required for POST /api/v1/chat. signIn is an OAuth 2.1 authorization-code flow with PKCE and the cedric:standard scope, accepted alongside the key on POST /api/v1/files and POST /api/v1/mcp; tokens from it always run in standard mode. Revoking the key is the off-switch.
What is the difference between a standard and a direct Cedric key?
Per the spec, a key's mode is chosen when it is created. Under a standard key, sends and writes Cedric would make wait for a person's approval; under a direct key they run immediately. Every caller acts as the key owner in their own workspace, with their access and the workspace's credits.
What are the rate limits for the Cedric API?
Per the spec, POST /api/v1/chat allows 30 requests per minute per key. POST /api/v1/files and POST /api/v1/mcp share 60 requests per minute per key, file uploads take up to 5 files of 100 MB each, and a tool-endpoint body can be up to 200,000 characters.
Is there a Cedric MCP server?
Yes - Cedric's spec includes an MCP endpoint at POST /api/v1/mcp. You can also connect the Cedric API directly through Jentic: your agent gets the full 3-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 a client config file, and your rules decide which operations the agent may call.
Can I limit what my agent is allowed to do with Cedric?
Yes. For example, write a rule that allows only POST /api/v1/chat, so your agent can ask Cedric questions and hand him tasks but cannot upload files or call his connected tools directly through the JSON-RPC endpoint. Pair it with a standard-mode key and Cedric's own sends still wait for approval, and every call your agent makes is logged.
How do I send Cedric a message through Jentic?
Add the Cedric API to your Jentic One instance from the directory and store your cedric_sk_ key. Your agent searches for 'ask Cedric to do a task', loads the runChatTurn operation, and posts a message with an optional session to keep context. To run it on your own infrastructure, install Jentic One from its GitHub repo.
GET STARTED