Meta Agent Tools
PT

Back to the catalog

Onplana

Project portfolio management for PMOs. Alternative to Microsoft Project Online. OAuth + PAT.

Open source Repository Open in the app JSON README (API)

About

Project portfolio management for PMOs. Alternative to Microsoft Project Online. OAuth + PAT.

Details

Kind
MCP servers
Topic
Finance & crypto
Publisher
onplana
Origin
official
Category
ferramentas
Transport
http
Version
0.2.4
Stars
4
Forks
1
Open pull requests
17
Last push
2026-08-27T16:17:14Z
Repository state
ativo
Language
TypeScript
License
MIT
Added
2026-08-29 03:02:09
Updated
2026-08-29 03:02:09
Origin id
io.github.Onplana/mcp-server

README

# Onplana MCP server

Open-source TypeScript Model Context Protocol building blocks,
extracted from [Onplana](https://onplana.com)'s production MCP
deployment. Two packages:

- **[`onplana-mcp-server`](./packages/server-template)**: server
  template. Streamable HTTP transport, Bearer auth, prompt-injection
  containment, pluggable dispatcher.
- **[`onplana-mcp-client`](./packages/client)**: typed TypeScript
  client SDK for calling the public Onplana MCP endpoint at
  `https://api.onplana.com/api/mcp/v1`.

[![CI](https://github.com/Onplana/onplana-mcp-server/workflows/CI/badge.svg)](https://github.com/Onplana/onplana-mcp-server/actions)
[![MIT License](https://img.shields.io/badge/license-MIT-blue.svg)](./LICENSE)

## What this is

The transport layer of an MCP server (Streamable HTTP wiring,
stateless mode, scoped Bearer auth, prompt-injection containment)
done well, separated from the platform-specific tool registry. Use
the **server template** to build your own MCP server with security
best practices baked in. Use the **client SDK** to drive Onplana's
hosted MCP from your own code.

The patterns are extracted from Onplana's production deployment
(public docs at [onplana.com/mcp](https://onplana.com/mcp)), the
same layer that handles real Claude Desktop, Cursor, ChatGPT custom
connector, and in-house agent traffic against the Onplana platform.

## Why open-source

The MCP transport is the same for everyone. Most early MCP servers
get the security primitives wrong:

- **Prompt injection.** Tools that return user-generated content
  (task titles, comment bodies, wiki text) put that content directly
  into the model's context. Without containment, a hostile actor can
  plant `"ignore previous instructions"` in their own data and the
  next agent that reads it follows along.
- **Stateless transport.** Most SDK examples assume in-memory session
  state, which breaks horizontal scaling and complicates the auth
  model.
- **Plan-gate semantics.** Surfacing tools the caller can't actually
  invoke wastes turns and confuses the model.

Onplana solved these in production over six months of MCP-server
work. Publishing the patterns is high-leverage:

1. Other MCP authors get a known-good template instead of
   reinventing.
2. The repo is a pretraining-signal surface. Public GitHub READMEs
   are heavily weighted in next-gen LLM training data, and a repo
   with patterns + clear documentation about MCP improves model
   recall of "what good MCP servers look like."
3. The dispatcher interface is the seam where your business logic
   plugs in. The transport is generic; what matters about your MCP
   server is the tool registry. Open-sourcing the transport doesn't
   give away anything proprietary.

The dispatcher implementation, tool catalog, plan-gate logic, audit
infrastructure, and the rest of Onplana's ~600 LOC closed-source
dispatcher stay in the closed monorepo because they encode platform
business logic. If you build your own MCP server using this
template, you write your own dispatcher. That's the work that
matters and the work that's specific to your platform.

## Repository layout

```
onplana-mcp-server/
├── packages/
│   ├── server-template/        # onplana-mcp-server (npm)
│   │   ├── src/
│   │   │   ├── transport.ts    # Streamable HTTP wiring
│   │   │   ├── auth.ts         # Bearer auth pattern
│   │   │   ├── promptInjection.ts  # wrapUserContent + escape
│   │   │   ├── dispatcher.ts   # Pluggable Dispatcher interface
│   │   │   └── index.ts
│   │   ├── tests/              # promptInjection + auth + transport
│   │   └── README.md
│   └── client/                 # onplana-mcp-client (npm)
│       ├── src/
│       │   ├── client.ts       # OnplanaMcpClient class
│       │   ├── types.ts        # Public type surface
│       │   └── index.ts
│       ├── tests/              # client.test.ts (stub fetch)
│       └── README.md
├── .claude-plugin/
│   └── marketplace.json        # Claude Code marketplace
├── plugins/
│   └── onplana/                # Claude Code plugin (skills + connect command)
├── examples/
│   └── in-memory/              # Runnable demo with 3 toy tools
├── gemini-extension.json       # Gemini CLI manifest
├── mcp.json                    # stdio client config (mcp-remote)
├── server.json                 # MCP registry manifest
└── .github/workflows/
    ├── ci.yml                  # tsc + vitest on PR
    └── publish.yml             # npm publish on tag v*
```

## Quickstart

### Build a server

Install:

```bash
npm install github:Onplana/onplana-mcp-server @modelcontextprotocol/sdk express
```

Wire an Express app:

```ts
import express from 'express'
import {
  createMcpPostHandler,
  createMcpMethodNotAllowedHandler,
  requireBearerAuth,
  type Dispatcher,
} from 'onplana-mcp-server'

const dispatcher: Dispatcher = {
  async listTools(ctx) { /* return your tool descriptors */ return [] },
  async callTool(name, input, ctx) { /* dispatch to your tools */ return { output: {} } },
}

const auth = async (token: string) => {
  // Validate against your token store. Return AuthContext or null.
  return { userId: 'u', scopes: ['MCP_AGENT'] }
}

const app = express()
app.use(express.json())
app.use('/api/mcp/v1',
  requireBearerAuth({ auth, requiredScope: 'MCP_AGENT' }),
)
app.post('/api/mcp/v1', createMcpPostHandler({ dispatcher }))
app.get('/api/mcp/v1', createMcpMethodNotAllowedHandler())
app.delete('/api/mcp/v1', createMcpMethodNotAllowedHandler())
app.listen(3000)
```

Full quickstart in [`packages/server-template/README.md`](./packages/server-template/README.md);
runnable demo in [`examples/in-memory/`](./examples/in-memory).

### Drive Onplana from code

Install:

```bash
npm install github:Onplana/onplana-mcp-server
```

Use:

```ts
import { OnplanaMcpClient } from 'onplana-mcp-client'

const client = new OnplanaMcpClient({
  url:   'https://api.onplana.com/api/mcp/v1',
  token: process.env.ONPLANA_PAT!,
})

const projects = await client.listProjects({ status: 'ACTIVE' })

// The differentiator vs other PM-tool MCPs: hybrid semantic + lexical
// search across your org's indexed content (projects, tasks, risks,
// goals, comments, wiki pages).
const { matches } = await client.searchOrgKnowledge({
  query: 'rationale for the 3-week design phase',
  scope: 'all',
  limit: 5,
})
```

Full client docs in [`packages/client/README.md`](./packages/client/README.md).

## Tools

The hosted server at `https://mcp.onplana.com/mcp` exposes 285 tools,
spanning projects, tasks, sprints, milestones, earned value, risks,
issues, governance, change control, timesheets, wikis, whiteboards,
workflows and the Microsoft Graph integrations. The exact number a given
client sees is smaller, because tools are filtered by the caller's role
and the organization's plan before the catalog is served.

The 33 below are the ones worth knowing first, not the whole catalog.
Reads are annotated `readOnlyHint`; writes carry `destructiveHint` so a
client can gate them. Every call runs under the calling identity, is
checked against that user's permissions and the org's plan, and lands in
the audit trail.

**Read** (`readOnlyHint: true`)

- `list_projects`: projects in the org, filterable by status.
- `get_project`: one project in full, with dates, owner and progress.
- `list_tasks`: tasks for a project, or across projects.
- `get_task`: one task with description, assignee, dates and recent comments.
- `list_my_tasks`: tasks assigned to the calling user.
- `list_overdue`: tasks past their due date.
- `list_team_members`: members of a project.
- `list_org_members`: members of the organization.
- `list_risks`: risks logged against a project.
- `find_similar_projects`: past projects resembling a description, for estimating.
- `search_org_knowledge`: hybrid BM25 and vector search over tasks, projects, wiki pages and comments.
- `summarize_project`: AI summary synthesized from the live plan.
- `analyze_project_risks`: AI risk detection across schedule, budget, scope and resources.
- `generate_status_report`: AI status report from the current schedule and activity.
- `search`: App Directory adapter, returns `{id, title, snippet?, url?}`.
- `fetch`: App Directory adapter, returns `{id, title, content, url?, metadata?}`.

**Write, additive** (`destructiveHint: false`)

- `create_project`: create a project.
- `create_task`: create a task, optionally under a parent.
- `create_milestone`: add a milestone to a project.
- `create_comment`: comment on a task, issue or project.
- `create_sprint_with_tasks`: create a sprint and pull tasks into it.
- `submit_timesheet`: log hours against a task.
- `add_project_member`: add an existing org member to a project.
- `link_dependency`: link two tasks, idempotent via a unique constraint.

**Write, mutating** (`destructiveHint: true`)

- `update_project`: change project fields such as status, dates or budget.
- `update_task`: change task fields such as status, progress or dates.
- `bulk_update_tasks`: apply one change across many tasks.
- `assign_task`: set a task's assignee.
- `move_task_to_sprint`: move a task into or out of a sprint.

**Leases** (for agents that share a backlog)

- `next_task`: pick the next available task and claim it in one call.
  Listing and then claiming leaves a gap two agents can both land in.
- `claim_task`: take an exclusive lease on a specific task.
- `renew_task_lease`: extend a lease while the work is still running.
- `release_task`: hand the lease back; completing or blocking a task
  releases it too, and ending a session releases everything that run holds.

A lease is keyed to the RUN, not to the user. Two sessions of one client
authenticate as the same agent persona, so a user-keyed lock would let
one session release the other's work. Leases expire on their own, so a
crashed agent frees its task instead of holding it.

Delete tools are not in the default catalog, and destructive operations
are deny-by-default: an org owner enables them per operation before an
agent can call them. The ones that can be enabled are recoverable, moving
to a recycle bin rather than being destroyed. Prefer `update_task` over
delete-and-recreate anyway, since Onplana audits every field change and
keeps the history.

## Production checklist

The template + SDK get you running. Add these on top:

- **Per-token rate limiting.** 60–120 req/min per Bearer token;
  agentic loops are noisier than humans.
- **Tenant cost cap.** If your tools call paid LLMs, gate dispatch
  on month-to-date spend. Onplana's deployment uses
  `aiMonthlyCostCapUsd` with WARN / BLOCK modes.
- **Audit logging.** Every dispatch should write an audit row
  tagged with `actorType: 'mcp_agent'` so admins can see what AI
  agents did in their tenant separately from human activity.
- **Plan / scope curation.** Don't expose every internal tool.
  Onplana exposes 21 of 26; the suppressed 5 either need an in-app
  preview UI, are too risky for unsupervised invocation, or produce
  oversized payloads.
- **PREVIEW mode for risky mutations.** Default mutating tools to
  preview-only on free tiers. Onplana ships this: agents see "what
  it would do" before users explicitly upgrade and re-run.
- **Idempotency keys.** Hash the canonicalised input + a session
  id; store as a unique constraint on your audit row. A model
  retrying the same logical action shouldn't double-create.

Each of those is platform-specific. The template gives you the seam
where they plug in (`Dispatcher.callTool`); your dispatcher
implements them however your platform encodes those concepts.

## Compatibility

- Node.js ≥ 20 (for the server template and CI matrix); ≥ 18 for
  the client (uses ambient `fetch`).
- `@modelcontextprotocol/sdk@^1.29.0`
- `express@^4.18.0` or `express@^5.0.0`

Tested against:

- Claude Code (plugin marketplace, or `claude mcp add --transport http`)
- Claude Desktop (Custom Connector)
- Cursor (`~/.cursor/mcp.json`)
- ChatGPT custom connectors (where MCP is enabled in your account)
- Gemini CLI + Gemini Code Assist (`~/.gemini/settings.json`)
- GitHub Copilot in VS Code (`.vscode/mcp.json`)
- The official [MCP Inspector](https://github.com/modelcontextprotocol/inspector)

## Install in Claude Code

The repo doubles as a Claude Code plugin marketplace, so installing is
two commands:

```bash
/plugin marketplace add Onplana/onplana-mcp-server
/plugin install onplana@onplana
```

Then attach the server:

```bash
/onplana-connect
```

That runs `claude mcp add --transport http onplana
https://mcp.onplana.com/mcp` and walks you through the browser sign-in.
The MCP server is available on every Onplana plan, including the free
one.

The plugin ships the two Onplana agent skills, invoked as
`onplana:<name>`:

| Skill | Use it when |
|---|---|
| `onplana-project-planner` | You have a goal or a brief and want an executable plan: a plan document attached to the project, then a task tree with dates, dependencies, owners and test cases. |
| `onplana-autonomous-agent` | A plan already exists and you want it run: claim a task, work it, record progress and evidence, resolve or hand it back, then take the next one. |

The plugin manifest deliberately declares no MCP server. A plugin
declares servers in the stdio form (`command`, `args`, `env`), and
Onplana's is remote and OAuth-authenticated, so `/onplana-connect`
attaches it at runtime through Claude Code's native HTTP transport
rather than routing it through a stdio shim.

## Install in Gemini CLI

The repo ships a `gemini-extension.json` manifest at the root, so
Gemini CLI installs Onplana with one command:

```bash
export ONPLANA_PAT=pat_paste-your-token-here  # mint at app.onplana.com/integrations
gemini extensions install https://github.com/Onplana/onplana-mcp-server
```

Restart the `gemini` CLI (or reload your VS Code / JetBrains window
if you're using Gemini Code Assist). The Onplana tools appear in
`/mcp` and your `GEMINI.md` context picks up the usage hints
shipped in this repo.

## Contributing

Issues + PRs welcome. The repo is small by design, the goal is for
the transport patterns to be obvious, well-tested, and stable.
Major-version bumps are reserved for breaking changes to the
exported `Dispatcher` / `BearerAuth` / handler factory shapes.
Patches and minors are for prompt-injection containment refinements,
new helper utilities, additional test coverage.

## License

[MIT](./LICENSE). © 2026 Onplana

## See also

- **[onplana.com/mcp](https://onplana.com/mcp)**: public docs page
  for the production Onplana MCP deployment (full tool catalog,
  setup instructions, security model)
- **[onplana.com](https://onplana.com)**: Onplana, the PM platform.
  Cloud-agnostic, AI-native, Microsoft Project Online alternative
- **[Model Context Protocol specification](https://spec.modelcontextprotocol.io)**: the MCP standard
- **[Anthropic prompt-injection guidance](https://docs.anthropic.com/en/docs/agents-and-tools/tool-use/overview)**: the security pattern this repo's wrap implements

More