canonical: https://jentic.com/apis/myagentda.com/myagentda

# Myagentda agentda

The agentda API serves a user's prioritized task agenda as rendered Markdown and exposes agentda's shared team knowledge base, where knowledge lives in topics referenced as T-1, T-2, and so on. Agents can list and create topics, save versioned Markdown documents of up to 4 MB into them, read any earlier version, and run a hybrid full-text and semantic search across every topic the user can see. Each topic also has a pull channel of what changed since a given time and a complete, append-only history, and topic admins can add writers or readers, switch visibility between private and workspace, rename, or archive a topic.

## For AI agents

Read a user's prioritized agenda as Markdown, search the shared agentda knowledge base, and save, version, and read Markdown documents inside knowledge topics.

## Scope

Does not create, complete, or reassign tasks, and it does not host files other than Markdown documents. Use for reading the agentda agenda and searching and writing its team knowledge topics only.

## Capabilities

- Fetch the user's prioritized agenda as Markdown with GET `/api/v1/agenda`, narrowing it with scope mine, delegated_by_me, or cc
- Search every visible topic with hybrid full-text and semantic matching through GET `/api/v1/knowledge/search`, optionally limited to one topic
- Save a Markdown document with a title, content_md, and source into a topic with POST `/api/v1/topics/{ref}/documents`
- Save a new version of a document with PUT `/api/v1/topics/{ref}/documents/{id}` and read an older one by passing version
- Pull what changed in a topic since a timestamp with GET `/api/v1/topics/{ref}/updates`, or read its full append-only history
- Create a private or workspace-visible topic with named writers and readers through POST `/api/v1/topics`
- Grant or revoke topic access, rename, or archive a topic with PATCH `/api/v1/topics/{ref}`

## Use cases

### A memory layer for your agent through Jentic

An agent that works across sessions needs somewhere durable to keep what it learns. Through Jentic it finds the agentda operations by intent, searches existing knowledge with GET `/api/v1/knowledge/search` before answering, and writes new findings with POST `/api/v1/topics/{ref}/documents`, passing a title, content_md, and a source such as the meeting or URL it came from. Teammates read the same topics, so the agent's notes are shared rather than locked in a chat log.

Example prompt: Call GET `/api/v1/knowledge/search` with q 'refund policy', and if no snippet answers the question, call POST `/api/v1/topics/T-3/documents` with title 'Refund policy summary', content_md containing the new findings, and source 'support call 2026-11-09'

### Daily agenda briefing

GET `/api/v1/agenda` returns the user's prioritized overview as Markdown: follow-ups due today, overdue tasks, tasks due today, tasks delegated to others, and remaining open tasks, with snoozed tasks hidden. The scope parameter narrows it to the user's own work, to tasks they delegated, or to tasks they only watch, so an assistant can answer 'what should I work on next' directly.

Example prompt: Call GET `/api/v1/agenda` with scope mine and summarize the overdue tasks and follow-ups due today in three bullet points

### Catching up on a topic

Topics never push changes, so staying current is a pull. GET `/api/v1/topics/{ref}/updates` returns chronological events since an ISO 8601 timestamp, covering new or changed documents, new members, and newly linked tasks. GET `/api/v1/topics/{ref}/history` returns the complete, append-only record when the full trail is needed.

Example prompt: Call GET `/api/v1/topics/T-2/updates` with since '2026-11-02T00:00:00Z' and list the documents that were added or changed

### Versioned documents without losing edits

Policies and specs get revised. PUT `/api/v1/topics/{ref}/documents/{id}` saves a new version while earlier versions stay readable through the version query parameter on GET, so an agent can compare the current text with an older version before proposing a change.

Example prompt: Call GET `/api/v1/topics/T-3/documents/{id}` with version 2 and again without version, then report what changed between the two

## Key endpoints

| Method | Path | Description |
| --- | --- | --- |
| GET | `/api/v1/agenda` | Get the prioritized task agenda |
| GET | `/api/v1/knowledge/search` | Search the knowledge base |
| POST | `/api/v1/topics/{ref}/documents` | Save a knowledge document |
| GET | `/api/v1/topics/{ref}/documents/{id}` | Read a document or an older version |
| PUT | `/api/v1/topics/{ref}/documents/{id}` | Save a new document version |
| GET | `/api/v1/topics/{ref}/updates` | Get what is new in a topic |
| POST | `/api/v1/topics` | Create a knowledge topic |

## Key resources

- **Agenda** — The user's prioritized task overview, rendered as Markdown and filterable by scope
- **Topics** — Shared knowledge scopes referenced as T-n, a unique name, or a UUID, with members, visibility, updates, and history
- **Documents** — Versioned Markdown documents of up to 4 MB stored inside a topic
- **Knowledge search** — Hybrid full-text and semantic search across visible topics, returning snippets

## 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:** 70 / 100
- **Maturity:** AI-Aware
- **Dimensions:**
  - Foundational Compliance: 100 / 100
  - Developer Experience & Jentic Compatibility: 63 / 100
  - AI-Readiness & Agent Experience: 63 / 100
  - Agent Usability: 94 / 100
  - Security: 50 / 100
  - AI Discoverability: 72 / 100
- **View full report:** https://jentic.com/apis/myagentda.com/myagentda/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 <openapi-url>
```

## Why Jentic

- **Setup:** Wiring agentda by hand means sending its access token in the Authorization header, resolving topic refs that can be a T-number, a name, or a UUID, and staying under the document write limit. Through Jentic you install once, import agentda from the API Directory, store the token once, and your agent calls it.
- **Permission scoping:** agentda puts the topic ref in the URL path (`/api/v1/topics/{ref}/...`), so a rule can pin your agent to one topic, such as T-3, and the operations you pick. You choose the operations it may call, so ones like deleting documents or changing topic members are not included unless you add them.
- **Credential handling:** Your agentda access token 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 'search the team knowledge base' or 'what is on my agenda', and Jentic returns the matching agentda operation with its input schema so the agent calls the right endpoint without browsing the reference docs.

## Related APIs

- **Notion API** — Pages, databases, and blocks in a general-purpose workspace
- **Coda API** — Docs with embedded tables and formulas
- **Asana API** — Team task and project tracking with full task editing
- **Linear API** — Issue tracking for product and engineering teams

## FAQ

### Is there an agentda MCP server?

You don't need an MCP server to give your agent agentda. Jentic connects it directly from the API Directory: import it, store your agentda access token once, and your agent calls it. Operations are discovered on demand, so no extra tool definitions sit in the agent's context.

### What authentication does the agentda API use?

Per its OpenAPI spec, agentda uses an access token sent in the Authorization header as Bearer followed by the token, and the raw token without the Bearer prefix is also accepted. The spec applies it to every operation. Through Jentic, the token is stored encrypted by your own Jentic One instance and injected at call time.

### Can I limit what my agent is allowed to do with the agentda API?

Yes. For example, write a rule that allows only GET `/api/v1/knowledge/search`, GET `/api/v1/topics/{ref}/documents/{id}`, and POST `/api/v1/topics/{ref}/documents` under topic T-3. Your agent can then search, read, and add notes in that one topic, but it cannot change members, archive topics, or delete documents, and every call it makes is logged.

### What are the rate limits for the agentda API?

The OpenAPI spec states a limit of 120 documents per hour per user for saving new documents with POST `/api/v1/topics/{ref}/documents.` It does not state a general request limit for the other operations.

### How do I save a note to agentda through Jentic?

Search Jentic for 'save a note to the team knowledge base', load the createTopicDocument operation, and call POST `/api/v1/topics/{ref}/documents` with the topic ref, a title, and content_md. Writing needs topic admin or writer access. To run it on your own infrastructure, install Jentic One from its GitHub repo.

### How do I refer to a topic in the agentda API?

The ref path parameter accepts the topic number such as T-3, the topic's unique name, or its UUID. Unknown topics, and topics the user cannot see, return 404, since visibility requires membership or a workspace-visible topic.

### Can agentda search find documents by meaning, not just keywords?

Yes. GET `/api/v1/knowledge/search` runs hybrid full-text and semantic search across all topics visible to the user and falls back to full-text when semantic search is unavailable. The q parameter needs at least 2 characters, and results are snippets, so fetch the full document with the document endpoint.