Sequential Thinking Working Notes

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/arben-adm-mcp-sequential-thinking

About

Use cases: note-taking, agent-memory

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.

Tools

3 read · 5 write · 2 delete · 1 not yet classified

Secrets

None asked for

Install scripts

None found

Runs as

Python package

Tools (11)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

• add_step

  Store one note with optional provenance or revision; URLs are not fetched.

• clear_historyClear History

  Delete all active database records in the local legacy session. Exports and backups remain; this is not secure erasure. Export first if needed. Returns: Status message with the number of thoughts that were cleared.

• create_session

  Start a local plaintext working log. No mandatory reasoning phases.

• delete_session

  Delete this session's active DB records; backups/exports survive. No secure erasure.

• export_sessionExport Session

  Export session_id to a file; omitted ID selects deprecated legacy format. Explicit sessions preserve IDs, branches, sources and completion in a worklog-session archive. Retry keys are excluded; use snapshots for full backup. file_path is confined to the storage directory's exports/ subdirectory — absolute paths and '..' traversal outside it are rejected. Args: file_path: Destination path, resolved against the exports/ directory Returns: Status message with the exported thought count.

• finalize_session

  Store an explicit completion at the expected version; infer no conclusions.

• generate_summaryGenerate Summary

  Summarize the recorded thinking process. Deprecated legacy workflow; prefer read_session for explicit sessions. Includes the actual thought content (excerpts per stage), aggregated challenged assumptions, open branches without a concluding thought, and revision chains, plus structural statistics (stage/branch/tag counts, stage coverage). This is a deterministic extraction from the recorded thoughts — it does not generate new reasoning or judge its quality. Returns: The summary (content + structure sections), or a "no thoughts recorded yet" message.

• import_sessionImport Session

  Import a session archive with its matching session_id; existing IDs conflict. Omitted session_id uses deprecated legacy import, REPLACING legacy history. Explicit archives preserve IDs and do not restore retry keys. file_path is confined to the storage directory's exports/ subdirectory — absolute paths and '..' traversal outside it are rejected. Args: file_path: Source path, resolved against the exports/ directory Returns: Status message with the imported thought count.

• list_sessions

  Find a previous session. Cursor is the last ID from the preceding page. version counts accepted mutations, not notes: it is the value to pass as expected_version, and says nothing about how many steps a session holds. Read the session to count those.

• process_thoughtProcess Thought

  Record one thought in the sequential-thinking audit trail. Validates and stores the thought (stage name, revision/branch consistency, per-line uniqueness of thought_number), then returns structural analysis: stage-order warnings, thoughts that are lexically related to this one, and progress counters. This does not evaluate, critique, or improve the reasoning — it only records and structures it. Args: thought: The content of the thought total_thoughts: The total expected thoughts in the sequence next_thought_needed: Whether more thoughts are needed after this one stage: The th…

• read_session

  Read bounded notes and caller-supplied completion; follow cursor for more. Every response names the view it used. Omitting view reads the resume view, or the steps view when kind, step_id or content_offset asks for a filter the resume view cannot apply; asking for both at once is rejected rather than answered in the other shape. The resume view is always active-only, so active_only applies to the steps view. In steps view, sequence is a database-wide pagination token, not a session count; use branch_id and position for numbering. Completion defaults to the first page and include_completion o…

Signals

Stars

959

Forks

121

Open issues

1

Weekly downloads

240

Last commit

Oct 23, 2026 (5 days ago)

Last release

Oct 21, 2026 (7 days ago)

Last package publish

Oct 21, 2026 (7 days ago)

From GitHub (fetched Oct 24, 2026) and the package registry.

Details

Registry name

io.github.arben-adm/mcp-sequential-thinking

Version

0.7.0

Auth

No auth

Packages

pypi mcp-sequential-thinking

License

MIT

Repository

github.com/arben-adm/mcp-sequential-thinking

First seen

Oct 24, 2026

Last checked

Oct 25, 2026

Source

Official MCP Registrygithub-graphql