Install Jentic One Beta

Connect the API Reference to your agent

Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the API Reference, 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%2Fprojectmanager.com%2Fprojectmanager" | 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%2Fprojectmanager.com%2Fprojectmanager" | 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 API Reference API.

Create tasks inside a project, link them with predecessor and successor dependencies, and nest them under parent tasks

Query tasks, projects, and time entries with $filter, $orderby, $top, and $skip parameters

Log time entries against a task and submit, approve, or reject a timesheet

Compare planned allocations with actual timesheet minutes for a task, grouped by resource

GET STARTED

Start building with API Reference API

Explore with Jentic One

View OpenAPI Document

Use Cases

Patterns agents use API Reference API for, with concrete tasks.

★ Agent-Managed Project Task Board

An AI agent connected through Jentic turns meeting notes into ProjectManager work: it creates tasks in the right project with a name, planned start and finish dates, and assignees, then links dependent tasks so the schedule reflects the real order of work. Because the project id sits in the URL path of task creation, the agent's access can be pinned to one project.

Create a task named 'Finalize vendor contract' in project 1a2b3c with plannedStartDate 2026-11-16 and plannedFinishDate 2026-11-20, then link it as a predecessor of the 'Kickoff' task

Timesheet Capture and Approval

Team members log hours through a chat assistant, which creates time entries with a date, hours, and the taskId they worked on. At the end of the week the assistant submits the timesheet, and a manager's agent approves or rejects submitted timesheets through the approval operations, keeping billable time current without manual form filling.

Create a time entry of 2 hours and 30 minutes on taskId 9f8e for 2026-11-12, then submit the timesheet for that date

Planned Versus Actual Effort Reporting

A project lead wants to see where effort is running over plan. The ProjectManager API returns planned allocations and actual timesheet minutes for a task, grouped by resource, and a resource workload query shows how loaded each person is. Together they let a reporting script flag overrun tasks and overallocated people before a deadline slips.

Read the planned allocations and actual timesheet minutes for task 9f8e and the workload for resource 42, and report whether either is over plan

Project Risk Register

Risks raised in standups or email are recorded against the project they affect, updated as they evolve, and tagged for triage. The risk register can then be exported for a steering review, so the record of open risks lives in ProjectManager rather than a separate spreadsheet.

Create a risk on project 1a2b3c describing a supplier delivery delay, then create a risk export for that project

Key Endpoints

273 endpoints — the projectmanager api plans and tracks projects, tasks, resources, and timesheets in a projectmanager workspace.

METHOD

PATH

DESCRIPTION

GET

/api/data/projects

Query projects

POST

/api/data/projects

Create a project

GET

/api/data/tasks

Query tasks

POST

/api/data/projects/{projectId}/tasks

Create a task in a project

PUT

/api/data/tasks/{taskId}

Update a task

POST

/api/data/timesheets

Create a time entry

POST

/api/data/timesheets/approvals

Submit a timesheet

GET

/api/data/workload/resources/{resourceId}

Query a resource's workload

GET

/api/data/projects

Query projects

POST

/api/data/projects

Create a project

GET

/api/data/tasks

Query tasks

POST

/api/data/projects/{projectId}/tasks

Create a task in a project

PUT

/api/data/tasks/{taskId}

Update a task

POST

/api/data/timesheets

Create a time entry

POST

/api/data/timesheets/approvals

Submit a timesheet

GET

/api/data/workload/resources/{resourceId}

Query a resource's workload

Why Jentic?

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

Setup

Wiring ProjectManager by hand means minting a bearer token, learning its OData-style $filter and $expand parameters, and mapping project, task, and timesheet ids across a large operation set. Through Jentic you install once, import ProjectManager from the API Directory, store the token once, and your agent calls it.

Permission scoping

ProjectManager puts the project id in the URL path for task creation, risk creation, members, and project fields (/api/data/projects/{projectId}/...), so a rule can pin your agent to one project for those operations. You choose the operations it may call, so destructive ones like project deletion or revoking all API keys are not included unless you add them.

Credential isolation

Your ProjectManager bearer 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 'create a task in a project' or 'submit a timesheet', and Jentic returns the matching ProjectManager operation with its input schema so the agent calls the right endpoint without browsing the reference docs.

FAQs

Specific to using API Reference API through Jentic.

What authentication does the ProjectManager API use?

The ProjectManager API authenticates with a bearer token in the Authorization header, declared in its OpenAPI spec as the scheme named oauth2 of type http bearer. Through Jentic the token is stored encrypted by your own Jentic One instance and injected at call time, so it never reaches the agent's prompt, logs, or context.

Can I log time and approve timesheets with the ProjectManager API?

Yes. You create time entries with a date, hours, minutes, and the taskId they apply to, then submit a timesheet for a date through the approvals operation. Separate approve and reject operations let a manager act on submitted timesheets.

What are the rate limits for the ProjectManager API?

The OpenAPI spec does not specify rate limits. Check https://developer.projectmanager.com for the current limits that apply to your account.

Is there a ProjectManager MCP server?

You don't need an MCP server to give your agent ProjectManager. Jentic connects it directly from the API Directory: import it, store your credential once, and your agent calls it. Operations are found on demand, so the full task, timesheet, and resource surface is reachable without loading every tool definition into the agent's context.

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

Yes. For example, write a rule that allows task creation and project risk creation under /api/data/projects/1a2b3c only, plus the time entry create operation, so the agent can add tasks and risks to that one project and log hours, while project deletion and timesheet approval stay out of reach. Every call it makes is logged.

How do I create a task in a project with the ProjectManager API through Jentic?

Import the ProjectManager API from the Jentic API Directory, store your bearer token once, and have your agent search Jentic for 'create a task in a project'. Jentic returns the operation for POST /api/data/projects/{projectId}/tasks with its input schema, where name is the required field. To run it on your own infrastructure, install Jentic One from its GitHub repo.

How do I filter tasks or time entries with the ProjectManager API?

The task, project, and timesheet query operations accept OData-style query parameters: $filter to narrow results, $orderby to sort, $top and $skip to page, and $expand to include related records. An agent can use these to pull only the tasks or entries it needs instead of reading the whole workspace.

Projectmanager API Reference

AI ReadinessFoundational (D+)49/100

See full scorecard

Official vendor OpenAPI document · agent-readyDeveloper ToolsProject Managementbearer273 EndpointsREST

For Agents

Create and update projects and tasks, assign resources, log and approve timesheets, track risks, and read resource workload in a ProjectManager workspace.

Use for: Create a task called 'Draft launch plan' in my website project, List all tasks in a project that are due this week, Log three hours against the design review task for today, Submit my timesheet for this week for approval

Not supported: Does not handle invoicing, payroll, or source code and CI pipelines. Use for project, task, timesheet, resource, and risk management in ProjectManager only.

The ProjectManager API plans and tracks projects, tasks, resources, and timesheets in a ProjectManager workspace. It creates projects and tasks, links tasks as predecessors and successors, assigns people, sets up recurring tasks and meetings, and records risks against a project. It also logs time entries, submits timesheets for approval, and reports planned allocations against actual timesheet minutes per task, with OData-style $filter, $orderby, $top, and $skip parameters on the main query operations.

Jentic One on Github View OpenAPI Document

Show dimension breakdown

Foundational Compliance

Base layer of spec validity and structural soundness.

Grade: A-Signals: 4

92%

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).

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: CSignals: 4

Example Density

How richly the API is illustrated with examples.

100%

Example Validity

Percentage of examples that conform to their schemas.

26%

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

80%

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.

61%

Summary Coverage

Coverage of summaries across operations/tags/info.

Agent Usability

Functional utility, complexity comfort, and AI orchestration readiness.

Grade: D-Signals: 1

43%

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

76%

Descriptive Richness

Clarity and depth of descriptions across API elements.

Connect the API Reference to your agent

Capabilities

Start building with API Reference API

Use Cases

Key Endpoints

Why Jentic?

Related APIs

FAQs

Projectmanager API Reference

Jentic AI Readiness Score

API Reference

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