Bump the npm group across 3 directories with 4 updates

[dependabot]

Bumps the npm group with 3 updates in the /mcp-client-typescript directory: @anthropic-ai/sdk, @modelcontextprotocol/client and dotenv.
Bumps the npm group with 2 updates in the /tests/helpers directory: @modelcontextprotocol/client and @modelcontextprotocol/server.
Bumps the npm group with 1 update in the /weather-server-typescript directory: @modelcontextprotocol/server.

Updates @anthropic-ai/sdk from 0.127.0 to 0.128.0

Release notes

Sourced from @​anthropic-ai/sdk's releases.

sdk: v0.128.0

0.128.0 (2026-09-22)

Full Changelog: sdk-v0.127.0...sdk-v0.128.0

Features

• api: add support for claude-opus-5-5, inline tool definitions and MCP tool-list pinning (beta) (eff2748)

Bug Fixes

• api: share one evaluated_permission enum across Managed Agents events (0c1cc0f)
• tools: addTools() takes effect straight away (#773) (1ccdad0)
• tools: leave reply-only params off the tool runner's compaction request (#769) (8afc336)

Chores

• docs: add descriptions to the Dreams API reference (ea4ddd1)
• docs: add descriptions to the User Profiles API reference (ea4ddd1)
• docs: add memory store descriptions to the Managed Agents API reference (ea4ddd1)
• docs: improve descriptions in the Dreams API reference (971c54a)
• docs: simplify the session thread agent type description (ccf71a2)
• docs: update diagnostics field descriptions on beta messages (c0b8746)
• internal: add property-based tests for partial JSON parsing (#776) (3ffac09)

Changelog

Sourced from @​anthropic-ai/sdk's changelog.

0.128.0 (2026-09-22)

Full Changelog: sdk-v0.127.0...sdk-v0.128.0

Features

• api: add support for claude-opus-5-5, inline tool definitions and MCP tool-list pinning (beta) (eff2748)

Bug Fixes

• api: share one evaluated_permission enum across Managed Agents events (0c1cc0f)
• tools: addTools() takes effect straight away (#773) (1ccdad0)
• tools: leave reply-only params off the tool runner's compaction request (#769) (8afc336)

Chores

• docs: add descriptions to the Dreams API reference (ea4ddd1)
• docs: add descriptions to the User Profiles API reference (ea4ddd1)
• docs: add memory store descriptions to the Managed Agents API reference (ea4ddd1)
• docs: improve descriptions in the Dreams API reference (971c54a)
• docs: simplify the session thread agent type description (ccf71a2)
• docs: update diagnostics field descriptions on beta messages (c0b8746)
• internal: add property-based tests for partial JSON parsing (#776) (3ffac09)

Commits

• 1926adb Merge pull request #1208 from anthropics/release-please--branches--main--chan...
• 162c8b1 chore: release main
• 3ffac09 chore(internal): add property-based tests for partial JSON parsing (#776)
• e40ce27 test(ecosystem): check that unused imports tree-shake to nothing
• 1ccdad0 fix(tools): addTools() takes effect straight away (#773)
• 8afc336 fix(tools): leave reply-only params off the tool runner's compaction request ...
• eff2748 feat(api): add support for claude-opus-5-5, inline tool definitions and MCP t...
• 06e5f9b codegen metadata
• 0c1cc0f fix(api): share one evaluated_permission enum across Managed Agents events
• c0b8746 chore(docs): update diagnostics field descriptions on beta messages
• Additional commits viewable in compare view

Updates @modelcontextprotocol/client from 2.0.0 to 2.1.0

Release notes

Sourced from @​modelcontextprotocol/client's releases.

@​modelcontextprotocol/client@​2.1.0

Minor Changes

• #2629 dcc0102 Thanks @​gbshankar! - Add DPoP (RFC 9449 / SEP-1932) sender-constrained access token support to the client.
  • Opt in by implementing OAuthClientProvider.dpop() returning a DpopSession (new, along with generateDpopKeyPair, accessTokenHash, isDpopNonceChallenge). auth() / exchangeAuthorization / refreshAuthorization / fetchToken then sign a DPoP proof into token requests (retrying once on an authorization-server use_dpop_nonce challenge, with client authentication re-applied per attempt), and StreamableHTTPClientTransport, SSEClientTransport and withOAuth present a token_type: "DPoP" access token as Authorization: DPoP <token> plus a fresh per-request proof, retry a resource-server use_dpop_nonce challenge once, and pick up a DPoP-Nonce delivered on any response. Tokens the AS issued as Bearer are still presented as Bearer.
  • DPoP is applied at the fetch layer: the transports wrap their resource-server fetch (including a caller-supplied fetch / eventSourceInit.fetch) with the new withDpopFromProvider(provider) middleware, so proofs are always bound to the request actually sent. withDpop(session, getToken) is exported for callers that manage tokens themselves (e.g. alongside a minimal AuthProvider); the AuthProvider interface itself is unchanged.
  • auth() now recovers from invalid_dpop_proof on refresh (e.g. a refresh token bound to a key that is no longer held) by discarding the tokens and re-authorizing, like invalid_grant. OAuthErrorCode gains InvalidDpopProof and UseDpopNonce; extractWWWAuthenticateParams recognizes the DPoP challenge scheme; OAuthMetadataSchema gains dpop_signing_alg_values_supported.

Patch Changes

• #2726 6fa4227 Thanks @​LuckTerence! - SdkError and SdkHttpError accept standard ErrorOptions as an optional fourth constructor argument and forward it to Error, so a wrapped error is reachable through the standard Error.cause chain. Version-negotiation probe failures (SdkErrorCode.EraNegotiationFailed) now use it: the underlying TypeError: fetch failed and the DNS or socket error beneath it surface via error.cause, so pino, Sentry, and util.inspect render ENOTFOUND / ECONNREFUSED / ETIMEDOUT instead of stopping at the SdkError (#2657). The previous error.data.cause slot is still populated for compatibility but is deprecated and slated for removal; read error.cause instead.

• #2654 03842cd Thanks @​pshah19! - Treat request id 0 as a real id. Two guards tested a RequestId for truthiness, so the legal JSON-RPC ids 0 and '' were read as absent. Id 0 is not a corner case: the outbound request counter is zero-based, so it is the first id every peer assigns, which on the server→client leg is the first sampling/createMessage, elicitation/create, or roots/list a server sends.

  • notifications/cancelled carrying id 0 was ignored, and the in-flight handler ran to completion with its AbortSignal never fired.
  • A notification sent with relatedRequestId: 0 wrongly passed the debounce gate (for methods opted into debouncedNotificationMethods). Because the pending set is keyed by method alone, a second such notification in the same tick was silently dropped rather than sent.

  Absent is now the only value that means "no id".

• #2043 c4248a9 Thanks @​ChrisJr404! - On Windows, stdio servers spawned by StdioClientTransport now also inherit COMSPEC, PATHEXT, PROGRAMDATA, PROGRAMFILES(X86), PROGRAMW6432, and WINDIR (added to DEFAULT_INHERITED_ENV_VARS). Programs a server launches can depend on them: PowerShell finds no native executables without PATHEXT, and Windows OpenSSH exits 255 without ProgramData.

• #2668 3e90449 Thanks @​KKonstantinov! - Stop sending notifications/cancelled for the initialize handshake. The spec is explicit that a client MUST NOT attempt to cancel its initialize request, but the outbound cancel path fired for any in-flight request: aborting the AbortSignal passed to connect(), or letting the handshake hit its timeout, put a forbidden cancellation on the wire naming the initialize request id.

  The local behaviour is unchanged — the caller's promise still rejects with the same abort/timeout error, and connect() still tears the connection down. Only the wire notification is suppressed. Every other method keeps the existing cancellation path.

• #2475 b654261 Thanks @​sanjibani! - StreamableHTTPClientTransport and SSEClientTransport now give their transport-managed headers precedence over same-named entries in requestInit.headers: Authorization when authProvider yields a token, mcp-protocol-version, and (Streamable HTTP) mcp-session-id. Header names compare case-insensitively and every HeadersInit form is covered (plain object, tuple array, Headers instance). Previously the caller-supplied value won, so a static Authorization placeholder (e.g. an env-var API key) kept overriding the OAuth token even after the provider obtained one and the fallback-to-OAuth flow never completed; a Headers instance or lowercase key produced a combined Bearer <fresh>, Bearer <stale> value instead. A configured Authorization is still sent while the provider has no token, and other configured headers pass through unchanged. Closes #2208.

• #2581 5119ee7 Thanks @​hugosmoreira! - Preserve the exact OAuth resource indicator from protected resource metadata when building authorization and token requests. Previously a pathless resource such as https://example.com was normalized to https://example.com/ via URL.href, which breaks authorization servers that require the resource parameter to match the published value exactly (Microsoft Entra ID rejects it with AADSTS9010010). The exported OAuth helpers (startAuthorization, exchangeAuthorization, refreshAuthorization, fetchToken, executeTokenRequest) now also accept a string for resource; selectResourceURL still returns a URL, and a provider's validateResourceURL result is used unchanged. Fixes #1968.

• 3924de9 - Let saveTokens failures surface after a successful token refresh. In auth(), one try wrapped both refreshAuthorization() and the provider.saveTokens() that persists its result, and the catch deliberately swallows anything that is not an OAuthError — plus ServerError — so that a failed refresh falls through to a fresh authorization request. A persistence error thrown by the provider landed in that same branch: it was discarded with no log and no rethrow, and auth() continued to startAuthorization() and returned 'REDIRECT'.

  Against an authorization server that rotates refresh tokens (the OAuth 2.1 default, and Keycloak's) this loses credentials rather than merely hiding an error. The exchange has already succeeded server-side, so the old refresh token is invalidated at the moment the new one is issued; dropping the new token set leaves nothing usable on either side. On a headless or CLI client, where redirectToAuthorization is typically a no-op, the fallthrough is silent and the client is left with stale tokens and no indication of why.

  The try/catch now covers only refreshAuthorization(). Persisting the result happens after it, on an unguarded path, so a provider's I/O error propagates to the caller.

  Refresh-request failures keep their existing control flow exactly: a ServerError or an unknown error still falls through to a new authorization flow, a non-ServerError OAuthError is still rethrown, and InsecureTokenEndpointError is still surfaced. The SEP-2352 issuer stamp written with the refreshed tokens is unchanged.

... (truncated)

Commits

• 9517506 Version Packages (#2808)
• 6a05402 fix(server): close StdioServerTransport when stdin ends or closes (#2494)
• c4248a9 fix(client): add missing Windows env vars to DEFAULT_INHERITED_ENV_VARS (#2043)
• 0b403f0 chore(changesets): only bump peer dependents when out of range (#2819)
• 6032170 feat(server): add request-time OAuth scope challenges (#1624)
• b654261 fix(client): let OAuth-derived Authorization override caller-supplied header ...
• 5ecc791 fix(codemod): only count real module specifiers in project-type inference (#2...
• 5119ee7 fix: preserve exact OAuth resource indicators (#2581)
• 6fa4227 fix(client): surface underlying network error via Error.cause on probe failur...
• dcc0102 feat(client): add DPoP (RFC 9449) sender-constrained token support (#2629)
• Additional commits viewable in compare view

Updates dotenv from 18.0.1 to 18.0.4

Changelog

Sourced from dotenv's changelog.

18.0.4 (2026-09-25)

Changed

• import dotenv/config should default quiet: true (#1063)

18.0.3 (2026-09-22)

Changed

• Patch DOTENV_QUIET setting when inside .env file (#1059)

18.0.2 (2026-09-21)

Changed

• Patch additional edge cases for the fast parser (#1056)

Commits

• 86804c0 18.0.4
• 2403db5 changelog
• 75b775e npm audit
• 7e1750c Merge pull request #1064 from motdotla/dependabot/npm_and_yarn/ip-address-10.7.2
• a6ade63 Merge pull request #1063 from motdotla/import
• 288b0d7 patch test
• 00da912 Bump ip-address from 10.2.0 to 10.7.2
• e6b5816 import 'dotenv/config' should still be defaulting to quiet
• 3646ac5 Merge pull request #1061 from motdotla/fast
• 83fc961 report dotenv vs native vs dotenv.fast
• Additional commits viewable in compare view

Updates @modelcontextprotocol/client from 2.0.0 to 2.1.0

Release notes

Sourced from @​modelcontextprotocol/client's releases.

@​modelcontextprotocol/client@​2.1.0

Minor Changes

• #2629 dcc0102 Thanks @​gbshankar! - Add DPoP (RFC 9449 / SEP-1932) sender-constrained access token support to the client.
  • Opt in by implementing OAuthClientProvider.dpop() returning a DpopSession (new, along with generateDpopKeyPair, accessTokenHash, isDpopNonceChallenge). auth() / exchangeAuthorization / refreshAuthorization / fetchToken then sign a DPoP proof into token requests (retrying once on an authorization-server use_dpop_nonce challenge, with client authentication re-applied per attempt), and StreamableHTTPClientTransport, SSEClientTransport and withOAuth present a token_type: "DPoP" access token as Authorization: DPoP <token> plus a fresh per-request proof, retry a resource-server use_dpop_nonce challenge once, and pick up a DPoP-Nonce delivered on any response. Tokens the AS issued as Bearer are still presented as Bearer.
  • DPoP is applied at the fetch layer: the transports wrap their resource-server fetch (including a caller-supplied fetch / eventSourceInit.fetch) with the new withDpopFromProvider(provider) middleware, so proofs are always bound to the request actually sent. withDpop(session, getToken) is exported for callers that manage tokens themselves (e.g. alongside a minimal AuthProvider); the AuthProvider interface itself is unchanged.
  • auth() now recovers from invalid_dpop_proof on refresh (e.g. a refresh token bound to a key that is no longer held) by discarding the tokens and re-authorizing, like invalid_grant. OAuthErrorCode gains InvalidDpopProof and UseDpopNonce; extractWWWAuthenticateParams recognizes the DPoP challenge scheme; OAuthMetadataSchema gains dpop_signing_alg_values_supported.

Patch Changes

• #2726 6fa4227 Thanks @​LuckTerence! - SdkError and SdkHttpError accept standard ErrorOptions as an optional fourth constructor argument and forward it to Error, so a wrapped error is reachable through the standard Error.cause chain. Version-negotiation probe failures (SdkErrorCode.EraNegotiationFailed) now use it: the underlying TypeError: fetch failed and the DNS or socket error beneath it surface via error.cause, so pino, Sentry, and util.inspect render ENOTFOUND / ECONNREFUSED / ETIMEDOUT instead of stopping at the SdkError (#2657). The previous error.data.cause slot is still populated for compatibility but is deprecated and slated for removal; read error.cause instead.

• #2654 03842cd Thanks @​pshah19! - Treat request id 0 as a real id. Two guards tested a RequestId for truthiness, so the legal JSON-RPC ids 0 and '' were read as absent. Id 0 is not a corner case: the outbound request counter is zero-based, so it is the first id every peer assigns, which on the server→client leg is the first sampling/createMessage, elicitation/create, or roots/list a server sends.

  • notifications/cancelled carrying id 0 was ignored, and the in-flight handler ran to completion with its AbortSignal never fired.
  • A notification sent with relatedRequestId: 0 wrongly passed the debounce gate (for methods opted into debouncedNotificationMethods). Because the pending set is keyed by method alone, a second such notification in the same tick was silently dropped rather than sent.

  Absent is now the only value that means "no id".

• #2043 c4248a9 Thanks @​ChrisJr404! - On Windows, stdio servers spawned by StdioClientTransport now also inherit COMSPEC, PATHEXT, PROGRAMDATA, PROGRAMFILES(X86), PROGRAMW6432, and WINDIR (added to DEFAULT_INHERITED_ENV_VARS). Programs a server launches can depend on them: PowerShell finds no native executables without PATHEXT, and Windows OpenSSH exits 255 without ProgramData.

• #2668 3e90449 Thanks @​KKonstantinov! - Stop sending notifications/cancelled for the initialize handshake. The spec is explicit that a client MUST NOT attempt to cancel its initialize request, but the outbound cancel path fired for any in-flight request: aborting the AbortSignal passed to connect(), or letting the handshake hit its timeout, put a forbidden cancellation on the wire naming the initialize request id.

  The local behaviour is unchanged — the caller's promise still rejects with the same abort/timeout error, and connect() still tears the connection down. Only the wire notification is suppressed. Every other method keeps the existing cancellation path.

• #2475 b654261 Thanks @​sanjibani! - StreamableHTTPClientTransport and SSEClientTransport now give their transport-managed headers precedence over same-named entries in requestInit.headers: Authorization when authProvider yields a token, mcp-protocol-version, and (Streamable HTTP) mcp-session-id. Header names compare case-insensitively and every HeadersInit form is covered (plain object, tuple array, Headers instance). Previously the caller-supplied value won, so a static Authorization placeholder (e.g. an env-var API key) kept overriding the OAuth token even after the provider obtained one and the fallback-to-OAuth flow never completed; a Headers instance or lowercase key produced a combined Bearer <fresh>, Bearer <stale> value instead. A configured Authorization is still sent while the provider has no token, and other configured headers pass through unchanged. Closes #2208.

• #2581 5119ee7 Thanks @​hugosmoreira! - Preserve the exact OAuth resource indicator from protected resource metadata when building authorization and token requests. Previously a pathless resource such as https://example.com was normalized to https://example.com/ via URL.href, which breaks authorization servers that require the resource parameter to match the published value exactly (Microsoft Entra ID rejects it with AADSTS9010010). The exported OAuth helpers (startAuthorization, exchangeAuthorization, refreshAuthorization, fetchToken, executeTokenRequest) now also accept a string for resource; selectResourceURL still returns a URL, and a provider's validateResourceURL result is used unchanged. Fixes #1968.

• 3924de9 - Let saveTokens failures surface after a successful token refresh. In auth(), one try wrapped both refreshAuthorization() and the provider.saveTokens() that persists its result, and the catch deliberately swallows anything that is not an OAuthError — plus ServerError — so that a failed refresh falls through to a fresh authorization request. A persistence error thrown by the provider landed in that same branch: it was discarded with no log and no rethrow, and auth() continued to startAuthorization() and returned 'REDIRECT'.

  Against an authorization server that rotates refresh tokens (the OAuth 2.1 default, and Keycloak's) this loses credentials rather than merely hiding an error. The exchange has already succeeded server-side, so the old refresh token is invalidated at the moment the new one is issued; dropping the new token set leaves nothing usable on either side. On a headless or CLI client, where redirectToAuthorization is typically a no-op, the fallthrough is silent and the client is left with stale tokens and no indication of why.

  The try/catch now covers only refreshAuthorization(). Persisting the result happens after it, on an unguarded path, so a provider's I/O error propagates to the caller.

  Refresh-request failures keep their existing control flow exactly: a ServerError or an unknown error still falls through to a new authorization flow, a non-ServerError OAuthError is still rethrown, and InsecureTokenEndpointError is still surfaced. The SEP-2352 issuer stamp written with the refreshed tokens is unchanged.

... (truncated)

Commits

• 9517506 Version Packages (#2808)
• 6a05402 fix(server): close StdioServerTransport when stdin ends or closes (#2494)
• c4248a9 fix(client): add missing Windows env vars to DEFAULT_INHERITED_ENV_VARS (#2043)
• 0b403f0 chore(changesets): only bump peer dependents when out of range (#2819)
• 6032170 feat(server): add request-time OAuth scope challenges (#1624)
• b654261 fix(client): let OAuth-derived Authorization override caller-supplied header ...
• 5ecc791 fix(codemod): only count real module specifiers in project-type inference (#2...
• 5119ee7 fix: preserve exact OAuth resource indicators (#2581)
• 6fa4227 fix(client): surface underlying network error via Error.cause on probe failur...
• dcc0102 feat(client): add DPoP (RFC 9449) sender-constrained token support (#2629)
• Additional commits viewable in compare view

Updates @modelcontextprotocol/server from 2.0.0 to 2.1.0

Release notes

Sourced from @​modelcontextprotocol/server's releases.

@​modelcontextprotocol/server-legacy@​2.1.0

Patch Changes

• Updated dependencies [dcc0102]:
  • @​modelcontextprotocol/core@​2.1.0

@​modelcontextprotocol/server@​2.1.0

Minor Changes

• #1624 6032170 Thanks @​SamMorrowDrums! - Add request-time OAuth scope challenges for tools, resources, resource templates, and prompts. Each primitive's scopeChallenge callback receives the parsed request and verified authentication info, then either continues or returns the exact scope set for an insufficient_scope response. requireScopes provides a small helper for static all-of checks.

  createMcpHandler and Streamable HTTP transports return HTTP 403 with an insufficient_scope challenge before handler execution or SSE setup. The preflight is active whenever a registered primitive carries a scopeChallenge callback — there is no handler- or transport-level configuration. The challenge's WWW-Authenticate header is built by the same formatter as the bearer-auth 401/403 answers, and its resource_metadata parameter is derived from the verified AuthInfo: requireBearerAuth / verifyBearerToken now stamp their configured resourceMetadataUrl onto the AuthInfo they return (new optional AuthInfo.resourceMetadataUrl field), with a fallback to the well-known location for an HTTP(S) RFC 8707 resource identifier; the parameter is omitted when neither is available.

Patch Changes

• #2726 6fa4227 Thanks @​LuckTerence! - SdkError and SdkHttpError accept standard ErrorOptions as an optional fourth constructor argument and forward it to Error, so a wrapped error is reachable through the standard Error.cause chain. Version-negotiation probe failures (SdkErrorCode.EraNegotiationFailed) now use it: the underlying TypeError: fetch failed and the DNS or socket error beneath it surface via error.cause, so pino, Sentry, and util.inspect render ENOTFOUND / ECONNREFUSED / ETIMEDOUT instead of stopping at the SdkError (#2657). The previous error.data.cause slot is still populated for compatibility but is deprecated and slated for removal; read error.cause instead.

• #2654 03842cd Thanks @​pshah19! - Treat request id 0 as a real id. Two guards tested a RequestId for truthiness, so the legal JSON-RPC ids 0 and '' were read as absent. Id 0 is not a corner case: the outbound request counter is zero-based, so it is the first id every peer assigns, which on the server→client leg is the first sampling/createMessage, elicitation/create, or roots/list a server sends.

  • notifications/cancelled carrying id 0 was ignored, and the in-flight handler ran to completion with its AbortSignal never fired.
  • A notification sent with relatedRequestId: 0 wrongly passed the debounce gate (for methods opted into debouncedNotificationMethods). Because the pending set is keyed by method alone, a second such notification in the same tick was silently dropped rather than sent.

  Absent is now the only value that means "no id".

• #2668 3e90449 Thanks @​KKonstantinov! - Stop sending notifications/cancelled for the initialize handshake. The spec is explicit that a client MUST NOT attempt to cancel its initialize request, but the outbound cancel path fired for any in-flight request: aborting the AbortSignal passed to connect(), or letting the handshake hit its timeout, put a forbidden cancellation on the wire naming the initialize request id.

  The local behaviour is unchanged — the caller's promise still rejects with the same abort/timeout error, and connect() still tears the connection down. Only the wire notification is suppressed. Every other method keeps the existing cancellation path.

• #2698 7b781ed Thanks @​maxisbey! - Read Streamable HTTP request bodies with a size limit. Every SDK-owned body read — WebStandardStreamableHTTPServerTransport (and the Node transport built on it), createMcpHandler, toNodeHandler, and createMcpHonoApp's JSON pre-parse — now stops at 4 MiB by default (the limit the legacy SSE transport already uses; the Express adapter and stdio bound their reads too) and answers 413 Payload Too Large before anything is parsed. toWebRequest (when it reads the Node stream itself) now rejects once the body exceeds the limit with an error whose name is 'RequestBodyTooLargeError' and status is 413, and toNodeHandler answers that with 413; hand-wired callers of toWebRequest should handle the rejection or pass a pre-parsed body, and isLegacyRequest reports such a request as non-legacy

... (truncated)

Commits

• 9517506 Version Packages (#2808)
• 6a05402 fix(server): close StdioServerTransport when stdin ends or closes (#2494)
• c4248a9 fix(client): add missing Windows env vars to DEFAULT_INHERITED_ENV_VARS (#2043)
• 0b403f0 chore(changesets): only bump peer dependents when out of range (#2819)
• 6032170 feat(server): add request-time OAuth scope challenges (#1624)
• b654261 fix(client): let OAuth-derived Authorization override caller-supplied header ...
• 5ecc791 fix(codemod): only count real module specifiers in project-type inference (#2...
• 5119ee7 fix: preserve exact OAuth resource indicators (#2581)
• 6fa4227 fix(client): surface underlying network error via Error.cause on probe failur...
• dcc0102 feat(client): add DPoP (RFC 9449) sender-constrained token support (#2629)
• Additional commits viewable in compare view

Updates @modelcontextprotocol/server from 2.0.0 to 2.1.0

Release notes

Sourced from @​modelcontextprotocol/server's releases.

@​modelcontextprotocol/server-legacy@​2.1.0

Patch Changes

• Updated dependencies [dcc0102]:
  • @​modelcontextprotocol/core@​2.1.0

@​modelcontextprotocol/server@​2.1.0

Minor Changes

• #1624 6032170 Thanks @​SamMorrowDrums! - Add request-time OAuth scope challenges for tools, resources, resource templates, and prompts. Each primitive's scopeChallenge callback receives the parsed request and verified authentication info, then either continues or returns the exact scope set for an insufficient_scope response. requireScopes provides a small helper for static all-of checks.

  createMcpHandler and Streamable HTTP transports return HTTP 403 with an insufficient_scope challenge before handler execution or SSE setup. The preflight is active whenever a registered primitive carries a scopeChallenge callback — there is no handler- or transport-level configuration. The challenge's WWW-Authenticate header is built by the same formatter as the bearer-auth 401/403 answers, and its resource_metadata parameter is derived from the verified AuthInfo: requireBearerAuth / verifyBearerToken now stamp their configured resourceMetadataUrl onto the AuthInfo they return (new optional AuthInfo.resourceMetadataUrl field), with a fallback to the well-known location for an HTTP(S) RFC 8707 resource identifier; the parameter is omitted when neither is available.

Patch Changes

• #2726 6fa4227 Thanks @​LuckTerence! - SdkError and SdkHttpError accept standard ErrorOptions as an optional fourth constructor argument and forward it to Error, so a wrapped error is reachable through the standard Error.cause chain. Version-negotiation probe failures (SdkErrorCode.EraNegotiationFailed) now use it: the underlying TypeError: fetch failed and the DNS or socket error beneath it surface via error.cause, so pino, Sentry, and util.inspect render ENOTFOUND / ECONNREFUSED / ETIMEDOUT instead of stopping at the SdkError (#2657). The previous error.data.cause slot is still populated for compatibility but is deprecated and slated for removal; read error.cause instead.

• #2654 03842cd Thanks @​pshah19! - Treat request id 0 as a real id. Two guards tested a RequestId for truthiness, so the legal JSON-RPC ids 0 and '' were read as absent. Id 0 is not a corner case: the outbound request counter is zero-based, so it is the first id every peer assigns, which on the server→client leg is the first sampling/createMessage, elicitation/create, or roots/list a server sends.

  • notifications/cancelled carrying id 0 was ignored, and the in-flight handler ran to completion with its AbortSignal never fired.
  • A notification sent with relatedRequestId: 0 wrongly passed the debounce gate (for methods opted into debouncedNotificationMethods). Because the pending set is keyed by method alone, a second such notification in the same tick was silently dropped rather than sent.

  Absent is now the only value that means "no id".

• #2668 3e90449 Thanks @​KKonstantinov! - Stop sending notifications/cancelled for the initialize handshake. The spec is explicit that a client MUST NOT attempt to cancel its initialize request, but the outbound cancel path fired for any in-flight request: aborting the AbortSignal passed to connect(), or letting the handshake hit its timeout, put a forbidden cancellation on the wire naming the initialize request id.

  The local behaviour is unchanged — the caller's promise still rejects with the same abort/timeout error, and connect() still tears the connection down. Only the wire notification is suppressed. Every other method keeps the existing cancellation path.

• #2698 7b781ed Thanks @​maxisbey! - Read Streamable HTTP request bodies with a size limit. Every SDK-owned body read — WebStandardStreamableHTTPServerTransport (and the Node transport built on it), createMcpHandler, toNodeHandler, and createMcpHonoApp's JSON pre-parse — now stops at 4 MiB by default (the limit the legacy SSE transport already uses; the Express adapter and stdio bound their reads too) and answers 413 Payload Too Large before anything is parsed. toWebRequest (when it reads the Node stream itself) now rejects once the body exceeds the limit with an error whose name is 'RequestBodyTooLargeError' and status is 413, and toNodeHandler answers that with 413; hand-wired callers of toWebRequest should handle the rejection or pass a pre-parsed body, and isLegacyRequest reports such a request as non-legacy

... (truncated)

Commits

• 9517506 Version Packages (#2808)
• 6a05402 fix(server): close StdioServerTransport when stdin ends or closes (#2494)
• c4248a9 fix(client): add missing Windows env vars to DEFAULT_INHERITED_ENV_VARS (#2043)
• 0b403f0 chore(changesets): only bump peer dependents when out of range (#2819)
• 6032170 feat(server): add request-time OAuth scope challenges (#1624)
• b654261 fix(client): let OAuth-derived Authorization override caller-supplied header ...
• 5ecc791 fix(codemod): only count real module specifiers in project-type inference (#2...
• 5119ee7 fix: preserve exact OAuth resource indicators (#2581)
• 6fa4227 fix(client): surface underlying network error via Error.cause on probe failur...
• dcc0102 feat(client): add DPoP (RFC 9449) sender-constrained token support (#2629)
• Additional commits viewable in compare view

Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.

---

Dependabot commands and options

You can trigger Dependabot actions by commenting on this PR:

• @dependabot rebase will rebase this PR
• @dependabot recreate will recreate this PR, overwriting any edits that have been made to it
• @dependabot show <dependency name> ignore conditions will show all of the ignore conditions of the specified dependency
• @dependabot ignore <dependency name> major version will close this group update PR and st...

Description has been truncated