From 4d49d709889607f69d96658161b08a9671a5ffcd Mon Sep 17 00:00:00 2001 From: Mert Erbak <71733533+merterbak@users.noreply.github.com> Date: Tue, 18 Nov 2025 00:37:15 +0300 Subject: [PATCH 1/3] Add MCP-Grok to Community Servers (#3020) --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index a50b6f1a0a..40053069d6 100644 --- a/README.md +++ b/README.md @@ -854,6 +854,7 @@ A growing set of community-developed and maintained servers demonstrates various - **[GraphQL](https://github.com/drestrepom/mcp_graphql)** - Comprehensive GraphQL API integration that automatically exposes each GraphQL query as a separate tool. - **[GraphQL Schema](https://github.com/hannesj/mcp-graphql-schema)** - Allow LLMs to explore large GraphQL schemas without bloating the context. - **[Graylog](https://github.com/Pranavj17/mcp-server-graylog)** - Search Graylog logs by absolute/relative timestamps, filter by streams, and debug production issues directly from Claude Desktop. +- **[Grok-MCP](https://github.com/merterbak/Grok-MCP)** - MCP server for xAI’s API featuring the latest Grok models, image analysis & generation, and web search. - **[gx-mcp-server](https://github.com/davidf9999/gx-mcp-server)** - Expose Great Expectations data validation and quality checks as MCP tools for AI agents. - **[HackMD](https://github.com/yuna0x0/hackmd-mcp)** (by yuna0x0) - An MCP server for HackMD, a collaborative markdown editor. It allows users to create, read, and update documents in HackMD using the Model Context Protocol. - **[HAProxy](https://github.com/tuannvm/haproxy-mcp-server)** - A Model Context Protocol (MCP) server for HAProxy implemented in Go, leveraging HAProxy Runtime API. From ec5357226a2028a08494443e53d6f81fc3de016f Mon Sep 17 00:00:00 2001 From: adam jones Date: Mon, 17 Nov 2025 21:41:22 +0000 Subject: [PATCH 2/3] Update Claude Code GitHub Action from beta to v1 (#3018) Updates the Claude Code GitHub Action to use the stable v1 GA release instead of the beta version. ## Changes - Updates action version from `@beta` to `@v1` - Migrates `allowed_tools` to `claude_args: --allowedTools` - Migrates `custom_instructions` to `claude_args: --system-prompt` - Retains `additional_permissions` and `assignee_trigger` (both still supported in v1) ## Behavior The action continues to work the same way: - Triggers on `@claude` mentions in comments, reviews, and issues - Triggers when assigned to an issue as "claude" - Allows Claude to run Bash commands - Allows Claude to read CI results on PRs - Applies custom instructions for posting concise summaries --- .github/workflows/claude.yml | 13 +++++-------- 1 file changed, 5 insertions(+), 8 deletions(-) diff --git a/.github/workflows/claude.yml b/.github/workflows/claude.yml index b09fc3eb18..2b566cd24d 100644 --- a/.github/workflows/claude.yml +++ b/.github/workflows/claude.yml @@ -32,7 +32,7 @@ jobs: - name: Run Claude Code id: claude - uses: anthropics/claude-code-action@beta + uses: anthropics/claude-code-action@v1 with: anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }} @@ -42,10 +42,7 @@ jobs: # Trigger when assigned to an issue assignee_trigger: "claude" - - # Allow Claude to run bash - # This should be safe given the repo is already public - allowed_tools: "Bash" - - custom_instructions: | - If posting a comment to GitHub, give a concise summary of the comment at the top and put all the details in a
block. + + claude_args: | + --allowedTools Bash + --system-prompt "If posting a comment to GitHub, give a concise summary of the comment at the top and put all the details in a
block." From 28a313206c7f1350ba946a923044f2f05a5a54f1 Mon Sep 17 00:00:00 2001 From: adam jones Date: Mon, 17 Nov 2025 21:41:31 +0000 Subject: [PATCH 3/3] fix(ci): test failures should fail the build (#3019) The 'Check if tests exist' step was actually running tests with continue-on-error: true. If tests failed, it would set has-tests=false and skip the actual test step, making CI appear green even with failing tests. Simplified to use 'npm test --if-present' which: - Runs tests if a test script exists (and fails if tests fail) - Does nothing and exits 0 if no test script exists - Removes the need for the complex check logic Fixes the issue where PR #3014 had failing tests but CI was green. --- .github/workflows/typescript.yml | 14 +------------- 1 file changed, 1 insertion(+), 13 deletions(-) diff --git a/.github/workflows/typescript.yml b/.github/workflows/typescript.yml index 87717166f2..c99318bd78 100644 --- a/.github/workflows/typescript.yml +++ b/.github/workflows/typescript.yml @@ -41,21 +41,9 @@ jobs: working-directory: src/${{ matrix.package }} run: npm ci - - name: Check if tests exist - id: check-tests - working-directory: src/${{ matrix.package }} - run: | - if npm run test --silent 2>/dev/null; then - echo "has-tests=true" >> $GITHUB_OUTPUT - else - echo "has-tests=false" >> $GITHUB_OUTPUT - fi - continue-on-error: true - - name: Run tests - if: steps.check-tests.outputs.has-tests == 'true' working-directory: src/${{ matrix.package }} - run: npm test + run: npm test --if-present build: needs: [detect-packages, test]