"Everything Server crashes when multiple clients reconnect"
* In index.ts
- added a variable to hold the initialize timeout
- store the timeout in the oninitialized handler
- clear the timeout in the cleanup callback
* In roots.ts
- In the catch block of syncRoots, log the error to the console via .error rather than attempting to send to the client because the most probable case here is that we don't have a connection.
"Everything Server crashes when multiple clients reconnect"
* In index.ts
- added a variable to hold the initialize timeout
- store the timeout in the oninitialized handler
- clear the timeout in the cleanup callback
* In roots.ts
- In the catch block of syncRoots, log the error to the console via .error rather than attempting to send to the client because the most probable case here is that we don't have a connection.
* In simulate-research-query.ts
- remove redundant local variable in getTask
* Everywhere else, prettier.
- Use params.task instead of params._meta.task for task metadata
- Remove pollInterval from task requests (only available on result)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Implement graceful degradation for elicitation on HTTP transport:
- STDIO: Full elicitation works via sendRequest
- HTTP: Catches elicitation failure, uses default interpretation
- Task completes successfully on both transports
simulate-research-query now uses try-catch around sendRequest and
includes explanatory message when elicitation is skipped on HTTP.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Update documentation to reflect that simulate-research-query now sends
elicitation requests directly from the background task instead of using
the tasks/result side-channel approach.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Instead of waiting for the client to call tasks/result to trigger
elicitation, the server now sends elicitation/create directly from
the background process using sendRequest. This simplifies the flow:
- Server sends elicitation proactively when clarification is needed
- Client receives and handles it via existing elicitation handler
- Task resumes and completes after receiving the response
- Client's polling sees completed status
This approach avoids requiring the client to detect input_required
status and call tasks/result as a side-channel.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Fixes CI failures in PR #3220.
PR #3220 updated `mcp` library from 1.0.0 to 1.23.0, which caused test
failures due to a breaking change in `McpError` constructor API.
The `McpError` constructor now expects an `ErrorData` object instead of
a plain string message. This commit fixes the usage in `get_zoneinfo()`
function to use `ErrorData(code=INVALID_PARAMS, message=...)`.
```console
Error before fix:
AttributeError: 'str' object has no attribute 'message'
```
Also updates `mcp` dependency to >=1.23.0 in pyproject.toml to ensure
compatibility with the new API.
Add tools that demonstrate bidirectional MCP tasks where the server
sends requests to the client for async execution:
- trigger-sampling-request-async: Send sampling request with task
params, client creates task and executes LLM call in background,
server polls for completion and retrieves result
- trigger-elicitation-request-async: Same pattern for user input,
useful when user may take time to fill out forms
Both tools:
- Check client capabilities (tasks.requests.sampling/elicitation)
- Accept both CreateTaskResult and direct result responses
- Poll tasks/get for status updates
- Fetch final result via tasks/result
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add tasks capability with list, cancel, and requests.tools.call
- Add InMemoryTaskStore and InMemoryTaskMessageQueue from SDK experimental
- Add simulate-research-query tool demonstrating task lifecycle
- Task demonstrates working -> input_required -> completed status flow
- Uses elicitation for ambiguous queries when client supports it
Closes#3037🦉 Generated with [Claude Code](https://claude.ai/code)
Adds a GitHub Actions workflow that:
- Detects PRs that only modify README.md
- Comments explaining we no longer accept new server additions
- Directs contributors to the MCP registry instead
- Allows updates/removals via /i-promise-this-is-not-a-new-server
- Uses labels (readme: pending / readme: ready for review) for filtering
- Minimizes bot comment after confirmation to reduce clutter
Claude-Generated-By: Claude Code (cli/claude-opus-4-5=100%)
Claude-Steers: 10
Claude-Permission-Prompts: 0
Claude-Escapes: 0
Use Git CLI directly instead of GitPython index API to ensure proper
path validation and prevent option injection. The '--' separator ensures
file paths starting with '-' are handled correctly.
Add validation to ensure file paths are within repository boundaries
before staging. This prevents potential issues with relative paths
and improves overall robustness of the git_add function.
* fix: regenerate uv.lock after version bump in release script
When the release script bumps the version in pyproject.toml, it needs
to also regenerate the uv.lock file. Otherwise the lockfile becomes
out of sync and `uv sync --locked` fails in CI with:
"The lockfile at uv.lock needs to be updated"
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* fix: use --frozen instead of --locked in release workflow
The release script bumps the version in pyproject.toml, which causes
the lockfile to be out of sync (uv includes the package's own version
in the lockfile). Using --frozen skips the lockfile freshness check
while still using pinned dependency versions.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
---------
Co-authored-by: Claude <noreply@anthropic.com>
The update-packages job needs to push tags to the repository but was
missing the required `permissions: contents: write`. This caused the
workflow to fail with a 403 error when trying to push the version tag.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-authored-by: Claude <noreply@anthropic.com>
Import `BadName` from `git.exc` directly instead of accessing it via
`git.exc.BadName`, which pyright doesn't recognize as a valid attribute
access on the `git` module.
This fixes the pyright CI failures introduced by the recent security
patches (GHSA merges).
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
The syncRoots call should be idempotent, requesting roots if they haven't been yet for the session, but always retuning the cached roots otherwise. That could be deferred but setting the handler for roots_list changed note should not.
* In server/roots.ts
- only set the notification handler and call for initial roots list if the roots aren't already cached for this client.
* In server/index.ts
- in the oninitialized handler
- get the sessionId from the transport
- set a 350ms timeout to call syncRoots with the server and sessionId
- this delay cause it to run after the `notifications/initialized` handler finishes, otherwise, the request gets lost.
* All other changes attributable to prettier
Validate that repo_path arguments in tool calls are within the
configured --repository path when the --repository flag is set.
The fix:
- Adds validate_repo_path() that resolves paths and checks
containment using Path.relative_to()
- Resolves symlinks before comparison
- Maintains backward compatibility when --repository is not set
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Paul Carleton <paulc@anthropic.com>
