Skip to content

Latest commit

 

History

History
63 lines (32 loc) · 9.3 KB

CHANGELOG.md

File metadata and controls

63 lines (32 loc) · 9.3 KB

@modelcontextprotocol/server-sequential-thinking

2.2.0

Minor Changes

  • #5536 311c0fd @cliffhall - Serve Streamable HTTP as well as stdio (#576). --transport streamable-http serves the server on one /mcp endpoint, for 2026-07-28 and 2025-era clients alike, at HOST:PORT (127.0.0.1:3001 by default); stdio stays the default. Over HTTP the filesystem server requires its allowed directories on the command line, since it cannot ask a client for its Roots, and the sequential-thinking history belongs to the server process rather than to one connection.

Patch Changes

  • #5535 a5c60fa @cliffhall - Count the thought box's header rows toward its 1000-row cap, so a long branchId can no longer draw past it on stderr: line breaks in a branchId are shown as \r and \n, and a header too long for the cap is cut with a row saying how many characters it left out (#5526).

2.1.1

Patch Changes

  • #5435 8da06bc @cliffhall - Bound the thought box logged to stderr. Since the multi-line box, every row was padded to the thought's longest line, so a thought with one long line and many short ones logged their product: a 60 KB thought wrote 400 million characters and could exhaust the server's memory. The box is now at most 100 characters wide (longer lines, and a long branch ID in the header, wrap) and draws at most 1000 rows of thought text (it then says how many lines it left out), so the log no longer grows with the thought's line count times its longest line. The thought kept in the server's history and the tool result are unchanged.

2.1.0

Minor Changes

  • #5397 93f89b1 @cliffhall - Bound the thought history each connection keeps: at most MAX_THOUGHT_HISTORY thoughts (default 1000) are retained, the oldest dropped first and from its branch too, so a long-lived connection no longer grows memory without bound.

Patch Changes

  • #5361 9a1cdf3 @cliffhall - Draw a multi-line thought one row per line in the stderr thought box, sized to the longest line, instead of as one broken row (#5205)

  • #5352 59b7f9d @cliffhall - Remove the unused yargs dependency (and @types/yargs), so installing the server no longer pulls in yargs and its transitive packages.

  • #5374 c4d0cc4 @cliffhall - Trim the sequentialthinking tool description from 2,781 to 1,009 characters (about 566 to 198 tokens), so it fits the 1,024-character cap OpenAI and Azure OpenAI put on tool descriptions (#799). The "Key features" and "Parameters explained" sections are gone: each parameter is still described by the input schema, which is unchanged, and the guidance those field descriptions do not carry is kept (#4507).

2.0.0

Major Changes

  • #5118 5b400a6 @cliffhall - Move to the TypeScript SDK v2 packages (@modelcontextprotocol/server) from @modelcontextprotocol/sdk 1.x (#4856). Breaking for clients: the server now requires Node.js 24 or later; over stdio, a single incoming JSON-RPC message larger than 10 MiB now closes the connection (the SDK v2 default read-buffer cap; SDK 1.x buffered without a limit); an unknown tool name is rejected with JSON-RPC error -32602 instead of returning an isError result; error messages no longer carry the MCP error <code>: prefix, and input-validation messages name the field first (field: message); tool schemas in tools/list declare JSON Schema 2020-12 instead of draft-07; and tools no longer advertise execution.taskSupport.

Minor Changes

  • #5131 419200b @cliffhall - Serve the 2026-07-28 protocol revision alongside the 2025 era on stdio, through the SDK's serveStdio entry (#4852). The thought history lasts as long as the client's connection, on either era.

Patch Changes

  • #5144 d6fd666 @cliffhall - Pad the header row of the thought box logged to stderr to the border's width, so its right edge lines up with the rest of the box (#5108).

1.0.0

The first semantic version, resuming semver after the date-stamped releases (last 2026.8.31). It describes everything since 2026.8.31, and is the last release of the legacy-era server, on the 1.x MCP SDK.

Patch Changes

  • #5015 8a4139c @cliffhall - Advertise the sequentialthinking tool as readOnlyHint: false and idempotentHint: false. Every call appends to the server's thought history, and a call with both branchFromThought and branchId also appends to that branch, so the tool was never read-only or idempotent. destructiveHint and openWorldHint stay false. (#4721)

  • #4970 86806cc @cliffhall - Build the server with an exported createServer() factory and attach stdio only when index.js runs as the binary, so the server can be tested in-process. No change to the tool, its schemas or its results.

  • #5031 bc52d0e @cliffhall - The thought log on stderr no longer prints "undefined" in its headers: a revision with no revisesThought reads "Revision N/M", and a branch with no branchId reads "(from thought N)" with no ID. The box border is sized from the header's visible text, so colour escape codes no longer make it wider than its text.

  • #5053 c63255a @cliffhall - Stop shipping the compiled test helper dist/__tests__/helpers.js in the published package: the build now excludes everything under __tests__/, not just *.test.ts.

  • #5036 b5c5ccc @cliffhall - A branchId that names an Object.prototype key, such as "constructor" or "__proto__", now creates and lists its branch like any other id instead of failing the call. A call that fails no longer adds its thought to the history first, so thoughtHistoryLength counts only thoughts that were accepted.

  • #5087 09edf63 @cliffhall - Require @modelcontextprotocol/sdk 1.31.0 or later (was ^1.30.0), so an install can no longer resolve an SDK version affected by GHSA-6qxp-vccf-f47h. The advisory concerns the SDK's OAuth client, which this server does not use.