* fix(cli): report success from mcp-use typecheck (#2099)
`tsc --noEmit` prints nothing on a clean project, so `mcp-use typecheck`
exited 0 with no output at all, which is indistinguishable from the
command hanging or silently failing.
Print `[mcp-use] no type errors (<duration>ms)` on exit code 0, matching
the existing `[mcp-use] built ... (<duration>ms)` line from `build`.
Failing runs are untouched and still show only the compiler's own
diagnostics.
Closes#2083
* chore: enter canary prerelease mode
* chore(typescript): version packages (canary)
* chore: sync main into canary (#2119)
* chore(release): exit prerelease mode and publish npm README hotfix
Publishes mcp-use 2.0.1 and @mcp-use/inspector 20.0.1 with the repository README included in the mcp-use package tarball.
* chore(release): exit prerelease mode and publish npm README metadata hotfix
Publishes mcp-use 2.0.2 and @mcp-use/inspector 20.0.2 after preparing README metadata before npm publication.
* chore(release): exit prerelease mode and commit npm package README
Publishes mcp-use 2.0.3 and @mcp-use/inspector 20.0.3 with a committed package-root README.
* chore(release): exit prerelease mode and fix npm README assets
Fix npm README asset and repository links, publish mcp-use 2.0.4, and keep Inspector aligned at 20.0.4.
* Update libraries/typescript/packages/server/README.md
Co-authored-by: cubic-dev-ai[bot] <191113872+cubic-dev-ai[bot]@users.noreply.github.com>
Signed-off-by: Andrew Khadder <54488379+khandrew1@users.noreply.github.com>
* docs: sync migration guide link
---------
Signed-off-by: Andrew Khadder <54488379+khandrew1@users.noreply.github.com>
Co-authored-by: Enrico Toniato <2827496+tonxxd@users.noreply.github.com>
Co-authored-by: cubic-dev-ai[bot] <191113872+cubic-dev-ai[bot]@users.noreply.github.com>
* fix(cli): say whether `start` mounted the inspector (#2100)
* fix(cli): say whether start mounted the inspector
`mcp-use dev` advertises the inspector in its banner, but `mcp-use start`
says nothing about it and `${basePath}/inspector` 404s unless
`--with-inspector` was passed. With no hint, that reads as a broken
production build rather than an opt-in.
Plain `start` now prints that the inspector is not mounted and how to
mount it, and `--with-inspector` prints the URL it was mounted at, which
was previously silent too.
Closes#2084
* fix(cli): drop the inspector-not-mounted line from start
Per review: most people running start do not want the inspector, so
announcing its absence is noise. Plain start is now silent about the
inspector again, and only the --with-inspector path prints its URL.
Updates the spec, the changeset, and swaps the test to pin the silence
instead of the message.
* chore(typescript): version packages (canary)
* chore: upgrade changesets cli to 2.31.1 (#2121)
* fix(ci): pin pnpm in the docs workflow so the job can start (#2116)
The docs job fails in "Set up pnpm" before it generates anything:
Error: No pnpm version is specified.
pnpm/action-setup@v4 was used with no version:, so it falls back to
reading packageManager from package_json_file, which defaults to the
repository root. This repo has no root package.json, so the step could
never succeed and the check was red on every branch including main.
Pins 11.13.1, matching all nine action-setup uses in ci.yml and the
packageManager field in libraries/typescript/package.json.
* fix(cli): support package-manager dev arg forwarding (#2124)
* fix(cli): support package-manager dev arg forwarding (MCP-2549)
* chore: add MCP-2549 changeset
* fix(cli): normalize forwarded arguments across commands
* chore(typescript): version packages (canary)
* docs: fix TypeScript README links into the removed mcp-use package (#2114)
The v2 merge deleted libraries/typescript/packages/mcp-use, but the
TypeScript README still pointed at it in four places: the three logo
sources at the top of the page, and the documentation link at the bottom.
The logo now uses the absolute raw.githubusercontent.com URL that every
sibling package README already uses, and the docs link points at
packages/server, which is where the mcp-use package lives in v2 and what
the create-mcp-use-app and inspector READMEs already link to.
* fix(create-mcp-use-app): drop stale main field and give templates distinct descriptions (#2085)
* fix(create-mcp-use-app): drop stale main field and give templates distinct descriptions
Two small things in the scaffolded package.json, both visible as soon as
you generate a project.
main pointed at dist/index.js. v2 builds emit .mcp-use/build instead, so
that path never exists and main never resolves. These templates are apps
you run with mcp-use start, not packages anyone imports, and .mcp-use is
gitignored build output, so the field is dropped rather than repointed.
All three templates also carried the description 'an mcp-use server'.
--list-templates reads that field, so the three were indistinguishable
from the CLI, and every generated project inherited the same string.
Each now says what it actually gives you.
Closes#2080Closes#2081
* chore: add changeset for the template package.json fixes
* fix(create-mcp-use-app): stop discarding the template description
updatePackageJson overwrote description with a generic
"<name>: an mcp-use server" on every scaffold, so the per-template
descriptions only ever reached --list-templates and never the generated
project. It now fills that in only when the template has no description
of its own, which keeps the previous behaviour for templates without one.
* chore(typescript): version packages (canary)
* fix(client): stop leaking parent env to stdio servers (#2125)
Port the security fix from #1949 to the v2 client package and verify the child process receives only safe defaults plus explicitly configured variables.
Co-authored-by: VihaanAgarwal <72850668+VihaanAgarwal@users.noreply.github.com>
* chore(typescript): version packages (canary)
* fix(client): bound conformance auth scenarios (#2126)
* fix(client): make stdio errlog actually receive the child's stderr (#2086)
* fix(client): make stdio errlog actually receive the child's stderr
StdioConnectionManager takes an errlog stream and documents that the
child server's stderr is piped to it, but the transport was created
without stderr: "pipe". The SDK defaults to "inherit", which leaves
transport.stderr null, so the forwarding block guarding on it never
ran and the child's stderr always went to the parent instead.
Spawn with stderr: "pipe" by default, spread so an explicit mode in
server params still wins. Tests spawn real child processes: one checks
a custom errlog receives the output, one checks stderr: "ignore" still
opts out.
* chore: drop stray version.ts that does not belong on beta
Left over from a main checkout; packages/mcp-use does not exist on this
branch.
* fix(client): expose stderr mode on the public stdio APIs
Per review, the compatibility escape hatch only worked for callers that
built StdioConnectionManager directly. StdioConnector did not accept or
forward stderr and StdioServerConfig did not expose it, so users of the
normal public APIs could not opt back into inherited stderr.
- Add a StdioStderrMode of "pipe" | "inherit" | "ignore", default "pipe".
- Accept it on StdioConnector and StdioServerConfig, forward it into
StdioServerParameters, and thread it through the config path.
- Apply the default after the spread so an explicit stderr: undefined no
longer defeats it.
- Only forward transport.stderr when the mode leaves a readable stream.
- Pipe with { end: false } and unpipe on close, since errlog is
caller-owned and may be reused across reconnects.
- Handle stream errors instead of letting a destroyed errlog surface as
an unhandled 'error' event.
Tests now start the transport before asserting, so the non-pipe cases are
exercised against a real child instead of passing by construction.
* fix(client): handle errlog write errors
---------
Co-authored-by: Andrew Khadder <andrew@manufact.com>
* chore(typescript): version packages (canary)
* fix(inspector): block loopback proxy targets by default (#2134)
mountInspector defaulted oauthProxyAllowLoopback to true, and the standalone
CLI hardcoded it — including in the published Docker image, which runs the
CLI with NODE_ENV=production on a public port. A publicly reachable inspector
could therefore proxy requests to the host's loopback services (SSRF), while
RFC1918/metadata targets were already blocked.
- mountInspector: default allowLoopback to false; local dev tooling opts in
- CLI: allow loopback unless NODE_ENV=production; INSPECTOR_ALLOW_LOOPBACK
overrides either way
- Express-adapter test opts in explicitly (it proxies to its own 127.0.0.1
echo server); new regression test covers the default and the opt-in
* chore(typescript): version packages (canary)
* docs: add v2 changelog updates
* chore: remove retired beta release flow (#2141)
* fix: keep prerelease versioning visible to Knip (#2142)
* fix: patch dependency vulnerabilities (#2151)
* fix: patch vulnerable dependencies
* fix: use mcp-use in client demo servers
* chore(typescript): version packages (canary)
---------
Signed-off-by: Andrew Khadder <54488379+khandrew1@users.noreply.github.com>
Co-authored-by: Ayaan Gazali <ayaangazali.work@gmail.com>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Enrico Toniato <2827496+tonxxd@users.noreply.github.com>
Co-authored-by: cubic-dev-ai[bot] <191113872+cubic-dev-ai[bot]@users.noreply.github.com>
Co-authored-by: VihaanAgarwal <72850668+VihaanAgarwal@users.noreply.github.com>
The package tree in CONTRIBUTING still lists packages/mcp-use, which the
v2 merge deleted, and omits server, client and agent. A new contributor
following it looks for a directory that is not there and misses three of
the six packages.
Also corrects the build order note: the root build script runs
@mcp-use/client first, then mcp-use, then the rest.
The agent skills still teach `from "mcp-use/server"`, a subpath that was
removed before v2 went stable, so an agent following them writes code
that will not resolve.
Covers the 40 import lines whose symbols all exist on the package root.
The remaining 18 are left alone: they pull in OAuth providers, which live
under mcp-use/oauth/*, plus jwksVerifier and oauthProxy, which have no v2
equivalent at all.
* docs: the v1 compatibility bridge no longer exists in v2
The migration guide tells people they can stage a migration by keeping
`import { MCPServer, text } from "mcp-use/server"`. That export was
removed before v2 went stable, so the import does not resolve and the
advice sends migrating users down a path that fails immediately.
Replaces the staging section with what actually happened and points at
the package root, and drops the matching allowance from the cleanup step.
* docs: drop the compatibility bridge section entirely
Per review: the bridge was never part of the official release, so
documenting its removal keeps a beta remnant alive in the migration
guide. Removes the section rather than rewriting it.
The cleanup step keeps its correction, since v1 really did import from
mcp-use/server and migrating users still need to remove those.
The rules block instructs coding agents to import server APIs from
mcp-use/server. That subpath was removed before v2 went stable, so an
agent following this rule writes an import that does not resolve.
Points at the package root instead and says the subpath is gone, since
the rule is competing with v1 examples the model has already seen.
Both URL classes are false positives that the weekly Link Checker
workflow has re-reported three Sundays running (#1838, #1867, #1939):
- GitHub /stargazers pages serve 404 to non-browser clients as bot
mitigation; they load fine in a browser. Verified the same behavior
on unrelated repos' stargazers pages.
- api.star-history.com/svg intermittently returns 5xx; the badge it
serves is decorative.
Both patterns are anchored so they only skip these exact cases: the
plain repo URL and any future /svg-* endpoint still get checked.
* Set V2 as the default documentation version
* Reorganize documentation navigation and redirects
* Remove deprecated repository content
* Rename Manufact deployment guide
The v2 merge deleted libraries/typescript/packages/mcp-use, so 26 of the
86 relative links in examples/README.md are dead. This fixes the 17 that
have an exact home in the v2 tree: client examples moved to
packages/client/examples, and the server ones lost the features/ grouping
and renamed oauth/ to auth/.
The remaining 9 point at examples with no v2 counterpart at all, so
fixing them means dropping the entry or aiming it somewhere approximate.
Left untouched pending a call on those.
The v2 merge deleted libraries/typescript/packages/mcp-use, which
context7.json still indexes, so none of the TypeScript examples are
reachable through Context7. v2 splits them into two packages, so the one
folder entry becomes two, and the conformance exclusion moves with them.
The templates table and the templates page both list meal-plan and
recipe-suggestion under Tools for the Recipe Finder, but the server
registers those two as prompts, not tools. Querying the linked demo
server confirms it:
tools/list -> search-recipes, get-recipe
prompts/list -> meal-plan, recipe-suggestion
The distinction matters because a model can call a tool on its own but
cannot invoke a prompt, so anyone reading the table expects behavior
they will not get. #1883 is someone hitting exactly that.
update-mcp-sdk-fork.yml maintained the @mcp-use/modelcontextprotocol-sdk
version in libraries/typescript/packages/mcp-use. The v2 merge deleted
that package, and v2 depends on the upstream @modelcontextprotocol
packages instead, so the fork is referenced nowhere in the tree or the
lockfile.
Every path the workflow touches is gone: the package.json it reads, and
the tests/deno/deno.json it also rewrites. Its first run against the v2
tree would fail on the version check.
* fix: use hosted WebSocket tunnel relay
* fix: reattach tunnels across relay deploys
* fix: negotiate tunnel keepalive support
* refactor: remove spinner state and improve loading indicators in ViewRenderer and MCP Apps components
* fix(inspector): honor PORT env var in Docker image
The Dockerfile comment promised PORT controlled the listen port, but the
exec-form CMD pinned --port 8080, so PaaS platforms that inject PORT
(Cloud Run, Railway, Heroku, Render) routed traffic to a port nothing
listened on. Switch to shell-form CMD with ${PORT:-8080} and exec so
the node process stays PID 1 for signal handling.
Closes#1868
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* fix(inspector): quote PORT expansion in Docker CMD
An unquoted expansion word-splits a PORT value containing whitespace
into extra CLI arguments (e.g. PORT='8080 --help' injects --help).
Quoted, the value reaches --port as a single argument.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
The python-lint job installs ruff unpinned, so it always resolves to the
latest release. ruff 0.16.0 started formatting fenced code blocks inside
Markdown, which brought libraries/python/README.md into the scope of
`ruff format --check .` for the first time. Its quickstart examples were
never formatted that way, so the job now fails on every pull request that
touches libraries/python, regardless of what the change is.
Pin to 0.15.22, the newest release that passes both steps on current main.
This restores a reproducible check and leaves the Markdown question as a
deliberate choice rather than something a tool release decides.
Refs #1856
github-actions[bot]