# Synaplan MCP server

> Search your Synaplan knowledge base and long-term memories, ingest documents and chat through Synaplan's AI pipeline.

- Listing: https://mcp.tc/i/synaplan
- Connect: use the server's own URL `https://web.synaplan.com/mcp` (OAuth sign-in at the server); clients connect to it directly. The listing link is a page, not an MCP endpoint.
- Type: remote (Streamable HTTP)
- Auth: OAuth sign-in
- Category: [AI & Machine Learning](https://mcp.tc/c/ai-ml)
- Vendor: metadist
- Homepage: <https://synaplan.com>
- Repository: <https://github.com/metadist/synaplan>

## About

Synaplan is an open-source AI workspace. This server exposes an account's knowledge base and assistants as tools: semantic RAG search over documents, long-term memory search and storage, document ingestion, and chat answered through Synaplan's full pipeline. You can also browse chats, messages, task prompts and assistants.

It runs as a hosted streamable HTTP endpoint at web.synaplan.com, and Synaplan can also be self-hosted. Access needs a Synaplan API key sent in the X-API-Key header, or a Synaplan account. Everything is scoped to the authenticated account.

## What it can do

- Run semantic search over your vectorized documents
- Find document chunks similar to a given one
- Search and store long-term memories
- Add text documents to the knowledge base
- Get synthesized answers through Synaplan's chat pipeline
- List chats, read messages, prompts and assistants

## Tools (10)

- `synaplan_chat`: Send a message through Synaplan's full pipeline and return the synthesized answer.
- `rag_search`: Semantic search across the user's documents, returning relevant chunks with scores. (read-only)
- `memory_search`: Search stored long-term memories by semantic similarity. (read-only)
- `memory_add`: Store a new long-term memory such as a fact or preference.
- `file_ingest`: Add a text document to the knowledge base, chunked and embedded for retrieval.
- `rag_similar`: Find chunks similar to a given source message or document id. (read-only)
- `list_chats`: List the user's conversations, most recently updated first. (read-only)
- `get_messages`: Return the messages of one chat in chronological order. (read-only)
- `list_prompts`: List the user's available task prompts. (read-only)
- `list_assistants`: List assistants the user may use, with slug, name, description and version. (read-only)

## Example prompts

- "Search my Synaplan knowledge base for the contract renewal terms."
- "Remember that I prefer concise answers in German."
- "Add these meeting notes to my Synaplan knowledge base."
- "List my recent Synaplan chats and show the last messages of the newest one."

## Install

### Claude Code

1. Run this in a terminal, in your project folder:

```bash
claude mcp add --transport http synaplan https://web.synaplan.com/mcp
```

2. Start Claude Code, type `/mcp`, pick **synaplan** and choose **Authenticate**. A browser window opens for the metadist sign-in.

Add `--scope user` to make it available in every project, not just this one.

### Claude Desktop

1. Open **Customize → Connectors**, click **+ Add**, then **Add custom connector**.

2. Name it **Synaplan** and paste this URL:

```url
https://web.synaplan.com/mcp
```

3. Click **Add**, then **Connect**, and sign in when metadist asks.

Claude Desktop’s JSON config file only starts local servers. Remote servers go through Connectors, and connectors you add on claude.ai show up here too.

### claude.ai

1. Open the connector form on claude.ai. This button fills in the name and URL for you:

[Add to claude.ai](<https://claude.ai/customize/connectors?modal=add-custom-connector&connectorName=Synaplan&connectorUrl=https%3A%2F%2Fweb.synaplan.com%2Fmcp>) (opens connector settings)

2. Check that the URL reads `https://web.synaplan.com/mcp` and click **Add**.

3. Click **Connect** and sign in when metadist asks.

Free plans allow one custom connector. On Team and Enterprise plans an owner adds it under **Organization settings → Connectors**.

### ChatGPT

1. On chatgpt.com, go to **Plugins**, select **+**, then **Add custom MCP server**.

2. Enter a name for the server.

3. Under **Connection**, paste `https://web.synaplan.com/mcp` as the server URL, then for authentication choose **OAuth**. ChatGPT sends you to metadist to sign in.

4. Check **I understand and want to continue**, then select **Create as a plugin**.

Whether you can add a custom MCP server depends on your ChatGPT plan and your workspace permissions (in Business workspaces, admins and owners can).

### Cursor

[Add to Cursor](<https://cursor.com/install-mcp?name=synaplan&config=eyJ1cmwiOiJodHRwczovL3dlYi5zeW5hcGxhbi5jb20vbWNwIn0%3D>) (opens Cursor)

Or add it by hand to `~/.cursor/mcp.json` (all projects) or `.cursor/mcp.json` (this project):

`mcp.json`:

```json
{
  "mcpServers": {
    "synaplan": {
      "url": "https://web.synaplan.com/mcp"
    }
  }
}
```

Cursor shows **Needs authentication** next to the server. Click the button beside it to sign in.

### VS Code

[Install in VS Code](<https://vscode.dev/redirect/mcp/install?name=synaplan&config=%7B%22type%22%3A%22http%22%2C%22url%22%3A%22https%3A%2F%2Fweb.synaplan.com%2Fmcp%22%7D>) (opens VS Code)

Or from a terminal:

```bash
code --add-mcp '{"name":"synaplan","type":"http","url":"https://web.synaplan.com/mcp"}'
```

Or commit it to the repo in `.vscode/mcp.json`:

`.vscode/mcp.json`:

```json
{
  "servers": {
    "synaplan": {
      "type": "http",
      "url": "https://web.synaplan.com/mcp"
    }
  }
}
```

VS Code asks you to sign in the first time the server starts.

### Devin Desktop

1. Add it to `~/.config/devin/mcp_config.json` (macOS and Linux) or `%APPDATA%\devin\mcp_config.json` (Windows):

`mcp_config.json`:

```json
{
  "mcpServers": {
    "synaplan": {
      "serverUrl": "https://web.synaplan.com/mcp"
    }
  }
}
```

2. Refresh the MCP server list in Cascade and sign in when asked.

Devin Desktop is the new name for Windsurf. It reads `serverUrl` (or `url`) for remote servers.

### Codex

```bash
codex mcp add synaplan --url https://web.synaplan.com/mcp
codex mcp login synaplan
```

Or edit `~/.codex/config.toml` directly:

`config.toml`:

```toml
[mcp_servers.synaplan]
url = "https://web.synaplan.com/mcp"
```

### Gemini CLI

```bash
gemini mcp add --transport http synaplan https://web.synaplan.com/mcp
```

Then, inside Gemini CLI, run `/mcp auth synaplan` to sign in.

This adds it to the current project. Add `-s user` to use it everywhere.

### Any client

Most clients accept this shape. Some name the URL field differently: `serverUrl` in Devin Desktop, `httpUrl` in Gemini CLI’s settings file.

```json
{
  "mcpServers": {
    "synaplan": {
      "type": "http",
      "url": "https://web.synaplan.com/mcp"
    }
  }
}
```

Zed puts servers under `context_servers` in its settings. Cline needs `"type": "streamableHttp"`, or it assumes SSE.

Client only starts local servers? Bridge it with `npx -y mcp-remote https://web.synaplan.com/mcp`.

## Recent changes

- 2026-11-08 05:28 UTC: Tracking started: 10 tools read. Source: automatic check.

More on the History tab, with descriptions before and after for the newest entries: https://mcp.tc/i/synaplan#history (Atom feed: https://mcp.tc/i/synaplan/history.xml). It records what mcp.tc's anonymous checks saw, every 3 hours where the tool list can be read without sign-in; it is not a security review.

## Details

- Server version: 0.1.0
- MCP protocol version: 2025-11-25
- Last checked: 2026-11-18 (reachable, asks for credentials)
- Listed: 2026-11-08
- Updated: 2026-11-08

---
Source: https://mcp.tc/i/synaplan (mcp.tc is an independent directory, not affiliated with this server's publisher). Corrections: https://mcp.tc/report
