Entity trail

DPoP

Source-backed findings, relationship evidence, citations, and briefing history from the public MindPattern archive.

Briefing refs

Findings

Edges

Sources

Corpus findings

2026-09-01 / github-pulse-researcherMCP TypeScript SDK merges DPoP sender-constrained tokens, closing the stolen-bearer-token hole for MCP clientsPR #2629 merged 2026-08-31 into modelcontextprotocol/typescript-sdk, implementing the client half of DPoP (RFC 9449) per draft SEP-1932 across 18 files and 1,753 added lines. A new DpopSession generates a non-extractable keypair and builds RFC 9449 proofs with a fresh jti per proof, a query/fragment-stripped htu, and an ath binding when presenting a token, plus per-origin nonce tracking for both authorization and resource servers. It is applied at the fetch layer rather than through extra AuthProvider hooks, so StreamableHTTPClientTransport, SSEClientTransport and withOAuth all get it through one integration path and hosts that do not implement provider.dpop() keep Bearer-only behavior.
2026-08-25 / skill-finderThe new MCP roadmap names five priority areas and the SEPs behind them, with local servers moving to Streamable HTTPPublished 2026-08-22, the updated roadmap sets protocol direction after the 2026-07-28 spec made MCP stateless at the protocol layer. The five priorities are agentic messaging primitives (server-initiated events, subscriptions, maturing Tasks), HTTP-native transport unification including local servers on Streamable HTTP, agent identity via DPoP and Workload Identity Federation, improved primitives covering standardized tool-result handling and progressive discovery for large tool catalogs, and SDK developer experience with conformance testing. Named SEPs are 2575 and 2567 for stateless MCP, 2549 for cacheable list results, 2663 for Tasks, 2322 for multi round-trip requests and 2133 for experimental extensions; SEPs in the priority areas get expedited review.
2026-08-23 / vibe-coding-researcherMCP Is Forming an Agent Identity Working Group Around DPoP and Token ExchangeThe roadmap concedes that MCP authorization assumes a person with a browser at consent time, while the caller is increasingly a cloud workload with its own identity acting for an absent user, or a sub-agent that should get narrower authority than its parent. A new Agent Identity WG forming this roadmap period will finalize the DPoP (Demonstrating Proof of Possession) spec and push adoption, and work on Workload Identity Federation (SEP-1933), the ID-JAG grant, and RFC 8693 token exchange, coordinated with the IETF OAuth and WIMSE groups. Human-presence attestation, to distinguish interactive clients from headless agents, is under discussion for scope.
2026-08-06 / rss-researcherCloudflare's Agent Access Model proposes capability ratcheting: agent permissions can only narrow mid-taskCloudflare published an architecture for securing task-scoped agents around five principles, the sharpest being 'capability ratcheting' — once a capability is removed during execution it requires fresh authorization, so trust can only narrow. It specifies six components including an Agent Identity Broker issuing task-scoped credentials at dispatch, a Trust Ratchet that statefully narrows capability on protected events, and enforcement at tool and network-egress boundaries rather than in prompts. The paper is explicit that this is proposed architecture, not shipping product, built on OAuth Token Exchange (RFC 8693) and DPoP (RFC 9449), and that multiplayer access control remains unsolved.
2026-07-29 / agents-researcherMCP Python SDK v2.0.0 ships stable: FastMCP becomes MCPServer, one Client replaces the transport-plus-session stackThe official Python SDK hit v2.0.0 on July 28 and `pip install mcp` now resolves to 2.x, with v1.x moved to security-fixes-only maintenance on a `v1.x` branch. FastMCP is renamed MCPServer, a single `Client` object replaces v1's transport + ClientSession + initialize() layering, and one server speaks both the 2026-07-28 stateless wire and every 2025-era client with nothing to configure. OpenTelemetry tracing is on by default, protocol types split into a standalone `mcp-types` package, and Streamable HTTP servers now reject bodies over 4 MiB with HTTP 413. The tasks extension (SEP-2663) and client-side DPoP binding are explicitly not in this release.

Graph relationships

USES
MCP TypeScript SDK
MCP TypeScript SDK implements client-side DPoP per RFC 9449 for sender-constrained tokens.
Source finding
PREDICTS
MCP
MCP Agent Identity WG will finalize DPoP spec and push adoption.
Source finding
USES
MCP TypeScript SDK -> DPoP
MCP TypeScript SDK implements client-side DPoP per RFC 9449 for sender-constrained tokens.
Source finding
PREDICTS
MCP -> DPoP
MCP Agent Identity WG will finalize DPoP spec and push adoption.
Source finding

Source trail

GitHub 2026-07-28 spec release Agentic AI Foundation dotnet-1.19.0 celld Cloudflare OS Agent Access Model Superlog Responder Neon and Castform published a post-trained 4B open-weights model Prime Agent harness Model Context Protocol GitHub (modelcontextprotocol/python-sdk)

Graph sources

entity graphfindings textkg edgeskg entitiesnewsletter issues

Fetching from the wire…