Thoughtbox

Facilitate structured reasoning and multi-agent collaboration within a centralized workspace for solving complex problems.

CommunityOnlineAPI key requiredGlobalFreeRead-only

What it can do

  • Thoughtbox Gateway: Single entry point for all Thoughtbox operations. Routes to all handlers: init, cipher, thought, notebook, session, mental_models, deep_analysis. Operations: - get_state, list_sess
  • Observability Gateway: Query system observability data including metrics, health status, active sessions, and alerts. No session initialization required - connect and query directly. Operations: - hea
  • Thoughtbox Hub: Multi-agent collaboration hub for coordinated reasoning. Operations: - register: Register as an agent (args: { name: string, profile?: "MANAGER"|"ARCHITECT"|"DEBUGGER"|"SECURITY"|"RESE

What data it sees

Do you need an account

An API key from the service settings is required

Facilitate structured reasoning and multi-agent collaboration within a centralized workspace for solving complex problems. Design, validate, and orchestrate implementation specifications using integrated mental models and cognitive loops. Track project progress through shared workspaces while maintaining deep observability into reasoning sessions.

How to connect

How to connect Thoughtbox to Claude

The server address to paste into Claude settings:

https://thoughtbox--kastalien-research.run.tools

  1. Open Claude (claude.ai or the desktop app).
  2. Go to Settings → Connectors.
  3. Click Add custom connector.
  4. Paste the server address copied below into Remote MCP server URL and click Add.
  5. In a chat, click + → Connectors and switch the new connector on.

Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

Authorization

After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

How to connect Thoughtbox to ChatGPT

The server address to paste into ChatGPT settings:

https://thoughtbox--kastalien-research.run.tools

  1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
  2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
  3. Open Settings → Connectors and click Create.
  4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
  5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
  6. In a new chat open + → Apps/Connectors and enable the connector.

OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

Authorization

On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

How to connect Thoughtbox to Cursor

The server address to paste into Cursor settings:

https://thoughtbox--kastalien-research.run.tools

Fastest: click Open in Cursor below and confirm the prompt.

Manually:

  1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
  2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
  3. Save the file. The server appears in the MCP list; authorize it there if asked.

Authorization

If the service needs sign-in, an authorize button appears next to the server in the MCP list.

Server tool list (3)

Raw names from tools/list. Only developers need these.

thoughtbox_gatewaySingle entry point for all Thoughtbox operations. Routes to all handlers: init, cipher, thought, notebook, session, mental_models, deep_analysis. Operations: - get_state, list_sessions, navigate, load_context, start_new, list_roots, bind_root (init) - cipher (loads notation system) - thought (structured reasoning) - notebook (literate programming) - session (session management) - mental_models (reasoning frameworks) - deep_analysis (session pattern analysis) Stage enforcement is handled internally - you'll get clear errors if calling operations too early.
observability_gatewayQuery system observability data including metrics, health status, active sessions, and alerts. No session initialization required - connect and query directly. Operations: - health: System and service health check - metrics: Instant Prometheus query (PromQL) - metrics_range: Range query over time - sessions: List active reasoning sessions - session_info: Get details about a specific session - alerts: Get active/firing Prometheus alerts - dashboard_url: Get Grafana dashboard URL
thoughtbox_hubMulti-agent collaboration hub for coordinated reasoning. Operations: - register: Register as an agent (args: { name: string, profile?: "MANAGER"|"ARCHITECT"|"DEBUGGER"|"SECURITY"|"RESEARCHER"|"REVIEWER" }) - whoami: Get current agent identity - create_workspace: Create a collaboration workspace (args: { name, description }) - join_workspace: Join an existing workspace (args: { workspaceId }) - list_workspaces: List all workspaces - workspace_status: Get workspace status (args: { workspaceId }) - create_problem: Define a problem to solve (args: { workspaceId, title, description }) - claim_problem: Claim a problem to work on (args: { workspaceId, problemId }) - update_problem: Update problem status (args: { workspaceId, problemId, status, resolution? }) - list_problems: List problems (args: { workspaceId }) - add_dependency: Add dependency between problems (args: { workspaceId, problemId, dependsOnProblemId }) - remove_dependency: Remove dependency (args: { workspaceId, problemId, dependsOnProblemId }) - ready_problems: List problems ready to claim (args: { workspaceId }) - blocked_problems: List problems blocked by dependencies (args: { workspaceId }) - create_sub_problem: Create a sub-problem (args: { workspaceId, parentId, title, description }) - create_proposal: Propose a solution (args: { workspaceId, title, description, sourceBranch, problemId? }) - review_proposal: Review a proposal (args: { workspaceId, proposalId, verdict, reasoning }) - merge_proposal: Merge an approved proposal (args: { workspaceId, proposalId }) - list_proposals: List proposals (args: { workspaceId }) - mark_consensus: Mark a consensus decision (args: { workspaceId, name, description, thoughtRef, branchId? }) - endorse_consensus: Endorse a consensus marker (args: { workspaceId, markerId }) - list_consensus: List consensus markers (args: { workspaceId }) - post_message: Post to a problem channel (args: { workspaceId, problemId, content }) - read_channel: Read problem channel messages (args