sequentialthinkingLABSCO SUMMARY
Deterministic by design, and honest about the token bill.
Every request takes the same route — no adaptive shortcut that makes results hard to compare — and the parallel specialists mean six angles land before anything is synthesised. The project states the cost plainly: roughly 5-10x the tokens per call. Treat it as the tool for the decision that deserves it, not the default reasoning path.
What it is
A sequential-thinking server backed by a team of agents. Every thought runs the same fixed path: an initial synthesis, six specialists in parallel, then a final synthesis.
What you get
- One tool, sequentialthinking, taking a thought, its number, the planned total, and flags for revision, branching and extending
- Six specialists running simultaneously — Factual, Emotional, Critical, Optimistic, Creative and Meta-cognitive — each with its own thinking direction and time budget
- A synthesis agent that runs twice, at the start and the end, on the enhanced model
- A structured result carrying should_continue, a stop_reason, the recommended next thought number and suggested arguments for the next call
- Revision and branching: mark a step as a revision when an earlier conclusion was wrong, or branch from a prior step with a branch id
- Optional web research through ExaTools, attached to every agent except synthesis
- Six providers supported, each with an enhanced and a standard model: DeepSeek by default, plus Groq, OpenRouter, GitHub Models, Anthropic and Ollama
Requirements
Python 3.10+, uv or pip, and an API key for one of the supported providers — LLM_PROVIDER plus that provider's key, for example DEEPSEEK_API_KEY. EXA_API_KEY is optional and turns on research; without it the system runs on reasoning alone. Install from the repository, then add the mcp-server-mas-sequential-thinking command to your client with the environment set. Expect roughly 5-10x the tokens of a single-agent tool, since every call invokes several agents.
Setup effort
Build from source — git clone https://github.com/FradSer/mcp-server-mas-sequential-thinking.git
USE CASES
01
Pressure-testing a decision before you commit
One call surfaces the risks, the upside and the bias check together rather than in three separate prompts.
02
Correcting a step you got wrong
Send a revision rather than starting the chain over.
03
Exploring an alternative line of reasoning
Branch from an earlier step with a branch id and follow the other path.
04
Adding evidence to the reasoning
Set an Exa key and every specialist except synthesis can research as it thinks.
1 tool
Listed in project docs. Your client may show a different list.
BEFORE YOU INSTALL
What to know first
Tools you get
1 tool named in the project's documentation.
Requires
- Python 3.10+
- uv (recommended) or pip
- An API key for the provider LLM_PROVIDER selects, for example DEEPSEEK_API_KEY for DeepSeek (the default); Ollama needs none
Where it runs
The documented client runs the server on your machine.
INSTALLATION
Connect your client
This one is built from source rather than installed with a single command.
Server setup
TERMINAL
git clone https://github.com/FradSer/mcp-server-mas-sequential-thinking.git
cd mcp-server-mas-sequential-thinking
uv venv
uv pip install .MCP Clients
Any MCP client
ANY MCP CLIENT · JSON
{
"mcpServers": {
"sequential-thinking": {
"command": "mcp-server-mas-sequential-thinking",
"env": {
"LLM_PROVIDER": "deepseek",
"DEEPSEEK_API_KEY": "<YOUR_DEEPSEEK_API_KEY>",
"EXA_API_KEY": "<YOUR_EXA_API_KEY>"
}
}
}
}uv venv makes a .venv folder inside the clone and uv pip install . installs into it, so the command is at .venv/bin/mcp-server-mas-sequential-thinking in your clone; give your client that full path if it cannot find the command. LLM_PROVIDER picks one of deepseek, groq, openrouter, github, anthropic or ollama, and only that provider's key is needed (Ollama needs none). EXA_API_KEY is optional.
