MAXential Thinking MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MAXENTIAL_DB_PATH | No | Path to SQLite database file. Default: .maxential/thinking.db in working directory. Use :memory: for in-memory. | |
| MAXENTIAL_LOG_FILE | No | Path to log file for error logging. |
Capabilities
Features and capabilities supported by this server
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| thinkA | Add a numbered thought to your reasoning chain. Each call persists to SQLite automatically. On first call, a new session is created. Use for any multi-step reasoning — analysis, debugging, design, research. Subsequent thoughts are appended to the active branch (main by default). Do not use for simple, single-step answers. |
| reviseA | Replace a previous thought with updated reasoning. The original thought is preserved in revision history. Use when earlier thinking was wrong, incomplete, or superseded by new information. Persists to SQLite. Do not use to add new thoughts — use think instead. |
| completeA | Mark the thinking chain as complete with a final conclusion. Sets the session status to 'complete'. Use when reasoning has reached a definitive answer. The session remains accessible via session_load and session_list. Do not call if you plan to continue thinking — you can always add more thoughts. |
| resetA | Clear the in-memory thinking state and start a new session. The previous session's data remains in SQLite and can be loaded later with session_load. Destructive to current in-memory state only. Use when switching to an unrelated problem. Requires confirm=true to prevent accidental clearing. |
| branchA | Create a new reasoning branch and switch to it. Subsequent think calls go to this branch until you switch_branch. Use to explore an alternative approach without affecting the main thread. Each branch maintains its own thought sequence. Persists to SQLite. Use close_branch when a path is exhausted, or merge_branch to bring insights back to main. |
| switch_branchA | Switch which branch receives new thoughts. Omit branchId to return to main. After switching, all think and revise calls apply to the active branch. Read-only tools (get_thought, search, get_history) can access any branch regardless of which is active. Does not modify any data. |
| list_branchesA | List all reasoning branches with their status and thought counts. |
| get_branchB | Retrieve complete details of a specific branch. |
| close_branchA | Close a branch, marking it as no longer active. Optionally include a conclusion summarizing what was learned. Closed branches and their thoughts are preserved and remain readable. Use when a line of reasoning is exhausted or the answer is clear. Cannot be reopened. To bring findings back to main first, use merge_branch instead. |
| merge_branchA | Merge findings from a branch back into the main thread as a new thought on main. The branch is marked as merged afterward. Strategies: conclusion_only — adds only the branch conclusion to main; full_integration — adds all branch thoughts to main; summary — generates a condensed summary of the branch on main. Use after a branch has produced useful findings you want on the main thread. |
| get_thoughtA | Retrieve a specific thought by its number, including any tags and revision history. Read-only. Use to reference or review earlier reasoning without scrolling through the full history. |
| get_historyA | Retrieve the full thought history for the current session. Optionally filter to a specific branch or limit the number of results. Read-only. Returns thoughts in chronological order with their numbers, content, tags, and branch assignments. |
| tagA | Add or remove semantic tags on a thought. Tags are searchable via the search tool. Common tags: hypothesis, evidence, decision, finding, question, risk. Persists to SQLite. At least one of 'add' or 'remove' should be provided. |
| searchA | Search the current session's thoughts by text content, tags, or both. Text search is case-insensitive substring matching. Tag search requires all specified tags to be present. Optionally limit to a specific branch. Read-only. Returns matching thoughts with their numbers, content, and tags. |
| exportA | Export the thinking chain as formatted text. Markdown format produces a human-readable document with headers and structure. JSON format produces machine-parseable output of all thoughts, branches, and tags. Optionally export a single branch. Read-only. |
| visualizeA | Generate a diagram showing the thought chain structure and branch relationships. Mermaid format produces a graph suitable for rendering in GitHub, Obsidian, or documentation. ASCII format produces a plain-text diagram for terminal or inline display. Read-only. |
| session_saveA | Name and describe the current thinking session for later retrieval. Data is already persisted automatically — this adds a meaningful name and optional description. |
| session_loadA | Restore a previously saved thinking session into memory, replacing the current in-memory state. All thoughts, branches, and tags from the saved session are loaded. The current session's data is not lost — it remains in SQLite and can be loaded later. Use after session_list to find the session UUID. Replaces current working state. |
| session_listB | Browse available thinking sessions. Shows most recently updated first. |
| session_summaryA | Generate a compressed summary of a thinking session for token-efficient context loading. Includes key findings from conclusions, tagged thoughts, and branch results. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/BAM-DevCrew/MAXential-Thinking-MCP'
If you have feedback or need assistance with the MCP directory API, please join our Discord server