# In Parallel

> In Parallel is a paid MCP server for knowledge and memory. Ask Claude, Copilot or ChatGPT about your team's decisions, with meeting sources. It runs as a hosted remote server, so there is nothing to install locally.

- **Kind:** MCP server
- **Pricing:** Paid
- **Starting price:** $29 a month
- **Platforms:** Web, API, CLI
- **Website:** https://www.in-parallel.com/mcp
- **Repository:** https://github.com/in-parallel-oy/agent-plugin
- **MCP Registry name:** ai.in-parallel/in-parallel
- **Categories:** knowledge and memory, productivity
- **Listing updated:** 2026-11-15

## About

In Parallel keeps a shared record built from your meetings, and this server hands that record to AI tools. The notetaker extracts more than 100 types of observation from each meeting, including decisions, action items and risks, each linked to the meeting it came from. When a decision changes, the new one supersedes the old, so answers stay current.

Access is scoped to the person asking. Grants come at four depths, from status through to the meetings and documents underneath, by project, named person or role, and are re-checked on every call. Connected tools such as Slack and Teams add the surrounding conversation.

One endpoint serves each workspace. A plugin for Claude Code, Codex and Cursor installs with npx, and Claude Desktop or ChatGPT can add it from a plugin library. The plugin lets an assistant read briefings, meetings, decisions and wiki pages, and record findings for your team. MCP access is included in every plan, with reads free within fair use.

## Features

- **Cited answers:** Each decision, risk or to-do links to its source meeting.
- **Permission scoping:** Answers match what the asking person can already see.
- **Self-updating context:** Updates as meetings happen, with no export jobs.
- **Superseding decisions:** Newer decisions replace older ones in the record.
- **Record findings:** Assistants can write findings back for the team.
- **Multi-client plugin:** Setup command for Claude Code, Codex and Cursor.

## Good for

- Ask what the team decided about pricing
- Get a catch-up on a project
- See what needs your attention this week
- Record a finding for colleagues from your coding agent

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http in-parallel https://www.in-parallel.ai/mcp
```

### Claude Desktop (Settings → Connectors → Add custom connector)

```sh
https://www.in-parallel.ai/mcp
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "in-parallel": {
      "url": "https://www.in-parallel.ai/mcp"
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "in-parallel": {
      "type": "http",
      "url": "https://www.in-parallel.ai/mcp"
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "in-parallel": {
      "serverUrl": "https://www.in-parallel.ai/mcp"
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "in-parallel": {
      "type": "http",
      "url": "https://www.in-parallel.ai/mcp"
    }
  }
}
```

## FAQ

### What does it cost?

Professional is €29 per user a month and Business €69; Enterprise starts at 50 users.

### Are MCP reads billed?

Free within fair use, up to 10,000 per user a month pooled.

### Do AI agents need a seat?

No, agents need no seat.

### Can I try it first?

Billing is monthly with cancellation any month, so the first month acts as a trial.

### Is In Parallel free?

No. In Parallel is a paid product. Paid plans start at $29 a month.

### How do I add In Parallel to Claude Code?

Run this command in your terminal: claude mcp add --transport http in-parallel https://www.in-parallel.ai/mcp

### What are the best alternatives to In Parallel?

The closest alternatives to In Parallel are Codebase Memory, XERJ, Ha MCP, Claude Code Ultimate Guide and Nautilus Compass Memory.

## Alternatives

- [Codebase Memory](https://ai-powered.com/mcp/codebase-memory): Codebase Memory is an open-source MCP server for knowledge and memory.
- [XERJ](https://ai-powered.com/mcp/xerj): XERJ is an open-source MCP server for knowledge and memory.
- [Ha MCP](https://ai-powered.com/mcp/ha-mcp): Ha MCP is an open-source MCP server for productivity.
- [Claude Code Ultimate Guide](https://ai-powered.com/mcp/claude-code-ultimate-guide): Claude Code Ultimate Guide is an open-source MCP server for ai models and llm tooling.
- [Nautilus Compass Memory](https://ai-powered.com/mcp/nautilus-compass-memory): Nautilus Compass Memory is an open-source MCP server for knowledge and memory.
- [Concord MCP](https://ai-powered.com/mcp/concord-mcp): Concord MCP is a freemium MCP server for developer tools.
- [note1](https://ai-powered.com/mcp/note1): note1 is an MCP server for productivity.
- [CalderFlow](https://ai-powered.com/mcp/calderflow): CalderFlow is a free MCP server for design and media.

---
Source: https://ai-powered.com/mcp/in-parallel
