Thoughtbox MCP server
io.github.Kastalien-Research/thoughtbox·v1.0.3·65 starsExtended reasoning with structured processes, persistence, and workflow guidance
65 stars44 downloads/wk
Reviews
Write oneNobody has reviewed Thoughtbox yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Thoughtbox tools (15, 5 write)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
add_cellAdd a cell to a notebook (title, markdown, or executable code)
cell-operationsAdd, update, list, and retrieve cells
createwrite actionCreate a new headless notebook for literate programming with JavaScript or TypeScript support. Optionally use a pre-structured template for guided workflows.
executionwrite actionRun code cells and install dependencies
exportExport a notebook to .src.md format. Always returns the notebook content as a string. Optionally writes to a filesystem path if provided. - STDIO mode: Provide 'path' to write to local filesystem (content still returned) - HTTP mode: Omit 'path', use returned 'content' directly Both modes always receive the content, ensuring transport transparency.
get_cellGet complete details of a specific cell including content and execution results
install_depsInstall npm dependencies defined in the notebook's package.json
listList all active notebooks with their metadata
list_cellsList all cells in a notebook with their metadata
loadLoad a notebook from .src.md format. Accepts either a filesystem path OR content string (exactly one required). - STDIO mode: Provide 'path' to read from local filesystem - HTTP mode: Provide 'content' string (e.g., from previous export) Both approaches create an identical in-memory notebook.
notebookNotebook toolhost for literate programming with JavaScript/TypeScript. Create, manage, and execute interactive notebooks with markdown documentation and executable code cells. Each notebook runs in an isolated environment with its own package.json and workspace. ✨ NEW: Pre-structured templates for guided workflows - Use template: "sequential-feynman" for deep learning with Feynman Technique - Temp
notebook-managementwrite actionCreate, list, load, and export notebooks
run_cellwrite actionExecute a code cell and capture output (stdout, stderr, exit code)
thoughtboxStep-by-step thinking tool for complex problem-solving. Supports flexible reasoning: forward thinking (1→N), backward thinking (N→1), branching, and revision. Adjust your approach dynamically as understanding deepens. Use for: - Multi-step analysis and planning - Problems requiring course correction - Hypothesis generation and testing - System design and architecture decisions Patterns Cookbook: A
update_cellwrite actionUpdate the content of an existing cell
Public scan report
scanner v0.1.10 · 2026-10-01 · same rubric, same numbers if you re-run it
- Code scan69 source files scanned25/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitylocal package, no credentials required12/15
- Maintenancelast push 79 days ago12/15
- Maintainer identityregistry namespace matches repository owner; GitHub account older than a year9/10
How Thoughtbox compares
Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 89/100
- higher than 80% of 48,255 servers
- Tools
- 15
- the typical server has 7
- Tools that change things
- 33%
- typical: 0%. Fewer write tools means less an agent can break
- GitHub stars
- 65
- more than 95% of 28,688 servers
- Downloads a week
- 44
- more than 36% of 12,191 servers with a package
What its tools let an agent do: 8 read · 2 create · 2 change · 3 run or deploy
Install Thoughtbox in Claude Code, Cursor or VS Code
Runs npx -y @kastalien-research/thoughtbox on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add thoughtbox -- npx -y @kastalien-research/thoughtbox
What the publisher says
From the Thoughtbox repository's README, as published. We do not edit it. Read it on GitHub
Thoughtbox
Multi-agent collaborative reasoning that's auditable. Thoughtbox is an MCP server for structured, multi-agent reasoning, with a companion web app for workspace and inspection flows. Every step is recorded as a structured thought in a persistent reasoning ledger that can be visualized, exported, and analyzed.
Runtime modes: Local development can use filesystem or in-memory storage. Deployed mode uses Supabase-backed storage, and the current production MCP server runs on Cloud Run.
Observatory UI showing a reasoning session with 14 thoughts and a branch exploration (purple nodes 13-14) forking from thought 5.
Code Mode
Thoughtbox exposes exactly two MCP tools using the Code Mode pattern:
- thoughtboxsearch** — Write JavaScript to query the operation/prompt/resource catalog. The LLM has full programmatic filtering power over the catalog.
- thoughtboxexecute** — Write JavaScript using the tb SDK to chain operations. Access thoughts, sessions, knowledge, notebooks, hub, observability, and protocol tools through a unified namespace.
Workflow: search to discover available operations, then execute code against them. Use console.log() for debugging — output is captured in response logs.
This replaces per-operation tool registration with a two-tool surface that scales without context window bloat.
Multi-Agent Collaboration
The Hub is the coordination layer. Agents register with role-specific profiles, join shared workspaces, and work through a structured problem-solving workflow — all via thoughtbox_execute.
The workflow: register → create workspace → create problem → claim → work → propose solution → peer review → merge → consensus
Workspace primitives:
- Problem — A unit of work with dependencies, sub-problems, and status tracking (open → in-progress → resolved → closed)
- Proposal — A proposed solution with a source branch reference and review workflow
- Consensus — A decision marker tied to a thought reference for traceability
- Channel — A message stream scoped to a problem for discussion
Agent Profiles: MANAGER, ARCHITECT, DEBUGGER, SECURITY, RESEARCHER, REVIEWER — each provides domain-specific mental models and behavioral priming.
28 operations across identity, workspace management, problems, proposals, consensus, channels, and status reporting.
Auditable Reasoning
Every thought is a node in a graph — numbered, timestamped, linked to its predecessors, and persisted across sessions. This creates an auditable trail of how conclusions were reached.
Agents can think forward, plan backward, branch into parallel explorations, and revise earlier conclusions. Each pattern is a first-class operation:
Each thought carries a semantic thoughtType (reasoning, decisionframe, actionreport, beliefsnapshot, assumptionupdate, contextsnapshot, progress) that classifies what kind* of thought it is, orthogonal to the process pattern used.
See the Patterns Cookbook for comprehensive examples.
Real-Time Observability
The Observatory is a built-in web UI at http://localhost:1729 for watching reasoning unfold live.
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
Thoughtbox: common questions
- Is Thoughtbox MCP server safe?
- Yes, by our scan: it is graded A (89/100). Read the Thoughtbox safety report
- How do I install Thoughtbox?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does Thoughtbox need an API key?
- Not as far as the registry entry and our scan can tell: no credentials are declared or required.
- Is Thoughtbox maintained?
- The last commit was 112 days ago (2026-07-15). The latest release is v1.0.3.
- How does Thoughtbox compare with other MCP servers?
- safety score 89/100 (higher than 80% of 48,255 servers); tools 15 (the typical server has 7); tools that change things 33% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.