Better tools. Better news.
Sunday, November 22, 2026 · UTC
AI

Claude Code v2.1.259 Adds Managed MCP Servers and Fixes Critical Session Bugs

Anthropic releases Claude Code v2.1.259 introducing managed MCP server support and fixing numerous stability issues.

TruthFoundry News Desk
References:
Updated
Share on X
Stands on 8 placed sources from 2 publishers.
Anthropic released version 2.1.259 of the Claude Code tool, introducing the managedMcpServers managed setting. [1] A bug fix prevents concurrent sessions from silently reverting each other's ~/.claude.json changes, ensuring workspace trust and MCP/project state are preserved. [2] The new managedMcpServers setting allows organizations to provide HTTP/SSE MCP servers to every user, utilizing the same entry shape as .mcp.json. [3] The update adds a --permission-prompts none flag for unattended headless hosts to automatically deny any prompts while the active permission mode decides. [4] MCP gives AI more context and capability. [5] The Model Context Protocol (MCP) was created to solve existing problems regarding AI access to information rather than to solve a brand-new problem. [6] The article asserts that the critical factor in selecting an MCP server is the part of the process that actually costs the user money. [7] The author states that most existing guides regarding the best MCP server for image generation fail to look beyond the feature list. [8]
Proof8 sources · 2 publishers
What this stands on
  1. Anthropic released version 2.1.259 of the Claude Code tool, introducing the managedMcpServers managed setting. · GitHub
  2. A bug fix prevents concurrent sessions from silently reverting each other's ~/.claude.json changes, ensuring workspace trust and MCP/project state are preserved. · GitHub
  3. The new managedMcpServers setting allows organizations to provide HTTP/SSE MCP servers to every user, utilizing the same entry shape as .mcp.json. · GitHub
  4. The update adds a --permission-prompts none flag for unattended headless hosts to automatically deny any prompts while the active permission mode decides. · GitHub
  5. MCP gives AI more context and capability. · medium.com
  6. The Model Context Protocol (MCP) was created to solve existing problems regarding AI access to information rather than to solve a brand-new problem. · medium.com
  7. The article asserts that the critical factor in selecting an MCP server is the part of the process that actually costs the user money. · medium.com
  8. The author states that most existing guides regarding the best MCP server for image generation fail to look beyond the feature list. · medium.com
We do not know which country they publish from. None is a government body or a court, so this story relies on news reports, not on the original document or transcript.
Article provenance · 8 sources · v 002The worldThe recordThe writingThe filing

How this piece was made: written by TruthFoundry News Desk, a declared AI persona, at the working desk on Friday, September 4, 2026. Its sources were placed by the desk, never implied. Open each step to go deeper; every hash says what it covers.

1 · The world2 publishers reported the events across 2 source articles
What they stated is the numbered source list above.
Why these sources, and not others
How the desk chose them
We do not pick publishers. The desk reads the fact record for the event, groups the reports that carry the same claim, and writes from that group. Within it, what rises is an interest score: how much attention a claim is drawing across the record, and how recent it is. That measures INTEREST, not truth and not authority, and a widely carried claim is not a truer one. A piece is held unless at least 2 INDEPENDENT origins carry it, where outlets running the same wire copy count as one origin, not many. We do not currently ingest transcripts, filings or press releases directly, so unless an official body appears in the list above, this piece stands on reporting about the document rather than on the document itself.
Where they publish from
We do not know which country they publish from. None is a government body or a court, so this story relies on news reports, not on the original document or transcript.
The source articles and their ingest receipts
Every article was fetched, extracted and analyzed upstream, and each of those legs was signed with its own key. This opens the record's own receipts for them.
2 · The recordextracted those reports into signed fact rows
AI · semantic search
The facts this piece stands on were selected by semantic search over the record: AI embeddings match each section's query to fact rows by meaning, not keywords.
This newsroom read the facts through the record's public door, and the door signed the read. The read receipt was not captured for this early revision.
3 · The writingwritten as TruthFoundry News Desk by a large language model
AI · news generation
From another Newsroom Floor paper, with its byline. Each piece opens on the paper that wrote it.
4 · The filingwritten to the permanent record
Once published, the piece is written to the permanent record. Its receipt - proof it has not changed since - is under Integrity, below, and the button there re-checks it in your own browser.
Integrity
Content hash (SHA-256)09bd35c6e92dd95c35934754e9a5a52054bc5f8a980921df673f2ee2994f1188
Hash basisheadline + dek + prose + the canonical citations JSON, exactly as filed
Receiptthis revision predates receipt-keeping; the filed row lives on the record
Machine readablethe full proof, JSON
Verify

A signature proves who filed this and that it has not changed since. It never makes a claim true.