Install Jentic One Beta

Connect the Pachca API to your agent

Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Pachca 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%2Fpachca.com%2Fpachca" | sh

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%2Fpachca.com%2Fpachca" | sh
jentic register       # connects your agent to your Jentic One instance

Jentic 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 Pachca API.

Send a message to a conversation, channel, thread, or user by setting entity_type and entity_id on POST /messages, with optional files and buttons

Search messages by text with filters such as chat_ids, user_ids, created_from, and created_to through /search/messages

Create a conversation or channel with member_ids and group_tag_ids, then add or remove members and change their roles

Create tasks with kind, content, due_at, priority, and performer_ids, optionally linked to a chat_id

GET STARTED

Start building with Pachca API

Explore with Jentic One

View OpenAPI Document

Use Cases

Patterns agents use Pachca API for, with concrete tasks.

★ Agent posts and replies in Pachca through Jentic

A team assistant agent posts summaries, alerts, and answers into Pachca chats. Through Jentic it finds the createMessage operation by intent, sets entity_type and entity_id for the target chat or thread, and sends the content, while your own Jentic One instance injects the Pachca bearer token at call time so the agent never sees it.

POST /messages with message.entity_type 'discussion', message.entity_id 334455, and message.content 'Release 2.4 is live', then pin it with POST /messages/{id}/pin

Searching team conversations

When someone asks where a decision was made, an agent searches the workspace instead of scrolling. GET /search/messages matches message text and attachment names in the chats the token can access, and can be narrowed with chat_ids, user_ids, and a created_from to created_to window; /search/chats and /search/users find the right chat or person first.

GET /search/messages with query 'invoice 1042', created_from '2026-11-01', and created_to '2026-11-08', then return the matching messages with their chat names

Task assignment from chat

Pachca tasks carry a kind, content, due_at, priority, and the performer_ids responsible, and can be linked to a chat. An agent that turns a chat request into a task creates it with POST /tasks, then lists or updates tasks as work progresses, so assignments stay inside the messenger the team already uses.

POST /tasks with task.kind 'reminder', task.content 'Send the contract to the client', task.due_at '2026-11-14T15:00:00Z', and task.performer_ids [12345]

Workspace administration and onboarding

Admins add new employees with POST /users, which sends an email invitation, assign group tags that grant chat access, and create channels for the new team. Audit events at /audit_events and member lists per chat let the same agent confirm who has access after the change.

POST /users with user.first_name 'Olga', user.last_name 'Petrova', user.email 'olga@example.com', and user.department 'Sales', then add her to chat 556677 with POST /chats/{id}/members

Key Endpoints

100 endpoints — the pachca api sends and manages messages in the pachca corporate messenger: it posts to conversations, channels, threads, and direct messages, edits and pins messages, adds reactions, and searches messages, chats, and users.

METHOD

PATH

DESCRIPTION

POST

/messages

Send a message

GET

/messages

List chat messages

GET

/search/messages

Search messages

POST

/chats

Create a conversation or channel

POST

/chats/{id}/members

Add chat members

POST

/tasks

Create a task

POST

/users

Create an employee

POST

/chats/exports

Order a message export

POST

/messages

Send a message

GET

/messages

List chat messages

GET

/search/messages

Search messages

POST

/chats

Create a conversation or channel

POST

/chats/{id}/members

Add chat members

POST

/tasks

Create a task

POST

/users

Create an employee

POST

/chats/exports

Order a message export

Why Jentic?

What agents get from Jentic-routed access to this vendor.

Setup

Wiring Pachca by hand means managing bearer tokens for users and bots, building nested message and task objects, and following cursor pagination across chat feeds. Through Jentic you install once, import Pachca from the API Directory, store the token once, and your agent calls it.

Permission scoping

Pachca puts chat, task, and user ids in the URL path for reads and changes, such as /chats/{id}/members and /tasks/{id}, so a rule can pin your agent to one chat's members or one task. New messages carry their target in the request body, so for posting, rules bound the operation, not the chat. You choose the operations, so destructive ones like deleting users or bots are not included unless you add them.

Credential isolation

Your Pachca 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.

Intent-based discovery

Agents search Jentic by intent such as 'send a message in Pachca' or 'create a task', and Jentic returns the matching Pachca operation with its input schema so the agent builds the right nested message or task object.

FAQs

Specific to using Pachca API through Jentic.

What authentication does the Pachca API use?

The Pachca API uses HTTP bearer authentication per its OpenAPI spec: a Pachca access token, such as a bot token issued with POST /bots/{id}/tokens, sent in the Authorization header. Through Jentic the token is stored encrypted by your own Jentic One instance and injected at call time, so it never enters the agent's prompt or logs.

How do I send a message to a thread or a user instead of a chat?

POST /messages takes a message object whose entity_type selects the target, one of discussion, thread, or user, and whose entity_id is that target's id. Set parent_message_id to reply to a specific message, and add files or buttons in the same object.

Can I export Pachca messages with the API?

Yes. POST /chats/exports orders an export of workspace messages between start_at and end_at, optionally limited by chat_ids, and can notify a webhook_url when the archive is ready. Download it afterwards with GET /chats/exports/{id}.

How do I post a message in Pachca through Jentic?

Install Jentic One, add the Pachca API from the Jentic API Directory, and store your Pachca token once. Your agent searches for 'send a message in Pachca', gets the createMessage operation with its input schema, and calls POST /messages with entity_type, entity_id, and content. To run it on your own infrastructure, install Jentic One from its GitHub repo.

Is there a Pachca MCP server?

You don't need an MCP server to give your agent the Pachca API. Jentic connects it directly from the API Directory: import it, store your credential once, and your agent calls it, with operations found on demand instead of loaded into its context up front.

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

Yes. Write a rule that allows GET /chats/556677, GET /chats/556677/members, and search only, plus POST /messages, and your agent can read that chat and post replies but cannot delete users, archive chats, or rotate bot tokens. Your own Jentic One instance logs what it calls.

Pachca API

AI ReadinessFoundational (D)46/100

See full scorecard

Official vendor OpenAPI document · agent-readyCommunicationsChat Messagingbearer100 EndpointsREST

For Agents

Post messages and threads in Pachca, search messages and employees, create chats and add members, assign tasks with due dates, and manage bots and their webhooks in a Pachca workspace.

Use for: Post the deployment summary to the engineering channel in Pachca, Search Pachca messages mentioning the invoice number from last week, I need to create a task for Anna due Friday, Create a new project channel and add the design team

Not supported: Does not place voice or video calls, send email or SMS, or manage calendars. Use for messaging, chats, tasks, and workspace administration in Pachca only.

The Pachca API sends and manages messages in the Pachca corporate messenger: it posts to conversations, channels, threads, and direct messages, edits and pins messages, adds reactions, and searches messages, chats, and users. It also creates and archives chats, manages chat members and roles, assigns tasks with due dates and performers, and administers employees, group tags, and statuses for the workspace. Bot owners can configure webhooks, read and delete webhook events, open forms with views, unfurl link previews, and order a message export for a period.

Jentic One on Github View OpenAPI Document

Show dimension breakdown

Foundational Compliance

Base layer of spec validity and structural soundness.

Grade: BSignals: 4

87%

Lint Results

Aggregated quality score from linter diagnostics, weighted by severity.

100%

Resolution Completeness

Percentage of `$ref` references that resolve successfully.

Specification Validity

Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).

75%

Structural Integrity

Structural correctness score based on schema issues using logarithmic dampening.

Developer Experience & Jentic Compatibility

Clarity, completeness, and ingestion readiness for developers and tooling.

Grade: A-Signals: 4

44%

Example Density

How richly the API is illustrated with examples.

99%

Example Validity

Percentage of examples that conform to their schemas.

51%

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.

AI-Readiness & Agent Experience

Semantic breadth, depth, and agent comprehension for AI systems.

Grade: FSignals: 4

85%

Description Coverage

Coverage of descriptions across API elements.

Error Standardization

Coverage of RFC 9457 Problem Details for error responses.

OperationId Quality

Coverage, uniqueness, and casing consistency of operationIds for AI inference.

Summary Coverage

Coverage of summaries across operations/tags/info.

Agent Usability

Functional utility, complexity comfort, and AI orchestration readiness.

Grade: ASignals: 1

85%

Complexity Comfort

Agent comfort level based on API operational and structural complexity.

Security

Trust, risk posture, and security compliance.

Grade: B-Signals: 1

60%

Authentication Strength

Average quality of security schemes based on authentication method strength (weakest link for OAuth2).

AI Discoverability

Findability, semantic richness, and reasoning readiness.

Grade: A-Signals: 1

75%

Descriptive Richness

Clarity and depth of descriptions across API elements.

Connect the Pachca API to your agent

Capabilities

Start building with Pachca API

Use Cases

Key Endpoints

Why Jentic?

Related APIs

FAQs

Pachca API

Jentic AI Readiness Score

Pachca API

Foundational Compliance

Lint Results

Resolution Completeness

Specification Validity

Structural Integrity

Developer Experience & Jentic Compatibility

Example Density

Example Validity

Response Coverage

Tooling Readiness

AI-Readiness & Agent Experience

Description Coverage

Error Standardization

OperationId Quality

Summary Coverage

Agent Usability

Complexity Comfort

Security

Authentication Strength

AI Discoverability

Descriptive Richness