The current mint CLI throws 'URIError: URI malformed' generating the anchor
slug for '### 100% Client Conformance (20/20)' (bare % followed by non-hex),
failing the 'Generate and validate API documentation' job on every PR.
Reworded to 'Full Client Conformance (20/20)'; mint broken-links now passes
across the whole docs tree.
Closes#1911
Co-authored-by: ayaanmacmini3 <ayaanmacmini3@ayaanmacmini3s-Mac-mini.local>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
* docs: reorganize navigation and clean up content
- Remove 'Misc' group with misplaced blog posts
- Remove 'Libraries' redirect group from Home nav
- Simplify 'Dev Tools' group (flatten Inspector, CLI, Tunneling)
- Remove individual changelog versions from Python nav (keep summary)
- Remove changelog from TypeScript 'Get Started' group
- Remove tunneling duplicate from Python Development group
- Rewrite mcp101 as clean MCP concepts page (was pitch deck)
- Delete typescript/blog posts (not technical docs)
- Add redirects for deleted blog post URLs
* docs: fix content accuracy and remove sloppy language
- Fix broken python/server/mcp-apps link in home page
- Remove informal pitch-speak from python/server/index.mdx
- Fix grammar error in typescript/server/index.mdx
- Update typescript/client/logging.mdx: remove fake 'coming soon' API code
- Fix non-existent model name gpt-5.1 in typescript quickstart
- Fix mcp_use naming in development contributing guide
* docs: fix incorrect TypeScript server API calls in inspector docs
- Replace server.addTool() with server.tool() (correct mcp-use API)
- Add missing zod import to debugging-chatgpt-apps example
* docs: fix fake model names (gpt-5.1 → gpt-4o) in agent docs
* docs: update model names, fix APIs, and add agent visibility hints
- Replace all deprecated model names with latest: gpt-4.1, gpt-4.1-mini,
claude-sonnet-4-6, claude-opus-4-7, gemini-2.5-flash across all docs
- Fix TypeScript server.tool() API in installation.mdx (old positional string form)
- Fix TypeScript agent.run() in quickstart.mdx (deprecated string form → object)
- Remove broken manufact.com/docs/llms.txt hidden hints from 5 pages
- Add <Visibility for="agents"> block to mcp101.mdx with install commands,
key classes, and API signatures for agent-oriented navigation
- Add LangChain provider install note to Python quickstart (mcp-use agent
requires a separate langchain-* provider package)
- Update model name cards in Python llm-integration.mdx
* docs: clean up remaining stale model names and improve accuracy
- Update supported model lists in Python and TypeScript llm-integration pages
- Fix cost optimization table to use current model IDs
- Update TypeScript agent overview supported providers list
* docs: add LangChain provider install to TypeScript quickstart agent section
The MCPAgent requires a separate @langchain/* provider package; this was
not mentioned before the code example that imports from @langchain/openai.
* docs: update to latest flagship model IDs (May 2026)
- OpenAI: gpt-4.1 → gpt-5.5, gpt-4.1-mini → gpt-5.5-mini
- Google: gemini-2.5-flash → gemini-3.1-flash, gemini-2.5-pro → gemini-3.1-pro
- Groq: llama-3.1-* → llama-4-scout-17b-16e-instruct
- Anthropic (claude-opus-4-7, claude-sonnet-4-6) already current, no change
* docs: replace all em dashes with hyphens
* docs: restore llms.txt hints using Visibility component
* docs: simplify TypeScript logging page to unsupported notice only
* docs: rewrite mcp101 to explain MCP protocol with mcp-use examples and doc links
* docs: remove goal.md
* docs: revert nav changes, keep only Misc group removal and blog redirects
* docs: reorder mcp101 to Server/App -> Client/Inspector -> Agent, restore title
* docs: add code examples for Resources and Prompts in mcp101
* docs: remove em dashes from mcp101
* docs: add MCPClient code examples to mcp101
* docs: add React client example to mcp101
* docs: add agent code examples to mcp101
* docs: expand MCP Apps section in mcp101 with example and links
* docs: restore Contacts, Socials, and Founders sections to mcp101
* docs: add context-setting intro paragraph to mcp101 for new readers
* docs: add MCP stores section to mcp101 intro with Claude, ChatGPT, Cursor
* docs: fix Claude store link
* docs: fix ChatGPT store link
* docs: fix Cursor store link
* docs: replace store Cards with linked image grid
* docs: add captions to store images
* docs: add Notifications to client primitives table in mcp101
* docs: add lead-in paragraph before resource cards at bottom of mcp101
* docs: move resource cards to end of page after Contacts/Socials/Founders
* docs: demote Contacts/Socials/Founders to bold text to remove from TOC
* docs: move Contacts/Socials/Founders to very end of mcp101
* docs: add Resources and Contacts section headers, link official MCP docs
* chore(docs): update site metadata, footer links, and rename mcp_use to mcp-use
* update docs metadata + images
* docs: enhance MCP section by highlighting the reach of MCP stores with 1 billion weekly active users
* api ref
- Add welcome page with py_welcome.png image
- Rewrite quickstart with Agent/Client/Server sections and mermaid diagram
- Simplify installation page (single package, no separate sections)
- Add updates symlink to changelog in getting-started
- Remove configuration overview page, update broken links to specific pages
- Update changelog title to "Updates"
- Replaced local image paths with CDN links for releases 1.3.11, 1.3.12, 1.4.0, 1.4.1, 1.5.0, and 1.5.2 in the changelog files.
- Updated the changelog entries to ensure consistent image sourcing and improve loading performance.
- Introduced a new Contributors component in the changelog files for releases 1.3.11, 1.3.12, 1.4.1, and 1.5.0 to acknowledge contributors in a consistent format.
- Updated the changelog entries to include a list of contributors for each release, enhancing visibility and appreciation for their contributions.
* chore(docs): remove Blog section from documentation
- Eliminated the Blog tab and its associated group from the documentation structure, streamlining the content for better clarity and focus on relevant topics.
* chore(docs): update image links in changelog and remove obsolete images
- Replaced local image paths with CDN links for releases 1.3.11, 1.3.12, 1.4.0, 1.4.1, and 1.5.0 in the changelog files.
- Deleted outdated image files for releases 1.3.11 and 1.3.12 to streamline documentation and reduce clutter.
* fix(docs): update documentation link for logo reference
- Changed the logo href from the main site to the documentation page for better navigation and user experience.
* chore: update imports
* refactor(mcpagent): update agent creation logic and imports
- Replaced `create_tool_calling_agent` with `create_agent` for improved agent instantiation.
- Simplified the `_create_agent` method by removing the `AgentExecutor` and directly returning the created agent.
- Adjusted type annotations for `_agent_executor` to initialize as `None` instead of using a union type.
* feat(mcpagent): migrate to LangChain 1.0.0 and simplify agent methods
- Updated MCPAgent to utilize LangChain 1.0.0's `create_agent()` for improved agent instantiation.
- Introduced new methods `astream_simplified()` and `run_v2()` that leverage the built-in `astream()` for internal agent loop handling.
- Retained legacy methods `stream()` and `run()` for backward compatibility with manual execution.
- Enhanced documentation to reflect changes and provide clearer usage examples.
* feat(mcpagent): implement dynamic tool updates during agent execution
- Enhanced the MCPAgent to support dynamic tool updates when using server_manager mode.
- Implemented logic to check for tool changes before and during execution, allowing for immediate updates and safe restarts.
- Introduced a maximum restart limit to prevent infinite loops during tool updates.
- Updated documentation to reflect the new behavior and usage of dynamic tool management.
* refactor(mcpagent): clean up imports and streamline logging
- Removed unused imports and organized existing ones for better clarity in `mcpagent.py`.
- Simplified logging statements for consistency and improved readability.
- Enhanced the overall structure of the code by eliminating unnecessary whitespace.
- Updated unit tests to reflect changes in imports and ensure compatibility with the refactored code.
* feat(mcpagent): enhance agent execution with step tracking and middleware
- Introduced `ModelCallLimitMiddleware` to enforce a maximum number of model calls during agent execution.
- Updated the `_consume_and_return` method to return a tuple of the final result and the number of steps taken.
- Enhanced telemetry tracking to include steps taken and execution time for better performance insights.
- Simplified agent creation logic by integrating middleware directly into the `create_agent` function.
- Improved logging for agent execution details, including steps and tool usage.
* fix(mcpagent): add null check for node output messages extraction
- Updated the MCPAgent to include a null check for `node_output` before attempting to access the "messages" key, preventing potential errors during message extraction.
* minor
* feat(mcpagent): filter out ToolMessage from history
- Updated the MCPAgent to exclude ToolMessage instances from being added to the message history, ensuring that only relevant messages are recorded.
- This change helps maintain a cleaner history by avoiding intermediate tool execution details.
* fix(mcpagent): set max_steps assignment
* ruff
* docs
* e2e tests for agent
* key in tests
* fix manager test and split ci tests
* telemetry off for tests
* fix server manager test
* feat(mcpagent): delegate query streaming to remote agent in remote mode
- recreated functionality to the MCPAgent to yield results from a remote agent when operating in remote mode, enhancing the agent's capability to handle queries efficiently.
* fix: agent unit tests
* Print inputs
* rollback, wrong repo
* fix streaming output
* stricter streaming test
* pass observability callbacks
* release notes
* update old release pages
* pyproject version bump
* if you do not want to migrate from langchain classic
* fix tests mock
* Canary Release (#391)
* feat(mcp-server): enhance widget metadata handling and resource domain configuration (#388)
* feat(mcp-server): enhance widget metadata handling and resource domain configuration
- Updated widget title handling to prioritize metadata title over the default name.
- Improved resource domain configuration to support dynamic server base URLs and include wildcard domains for better flexibility.
- Enhanced apps SDK metadata integration by merging additional metadata from widget configurations.
- Refactored HTML template handling for improved clarity and maintainability.
* changeset
* chore: enter canary prerelease mode
* chore(typescript): version packages (canary)
* feat: Enhanced widget integration and tunnel support (#389)
* refactor: streamline widget HTML generation and enhance logging
- Simplified base URL handling in the CLI by removing conditional MCP_URL usage.
- Updated HTML content generation in inspector utilities to improve base tag injection logic.
- Enhanced logging for better debugging and insights into widget content generation.
* feat: add tunnel support to CLI for server exposure
- Introduced a new `--tunnel` option in the CLI to expose the server through a tunnel.
- Implemented `startTunnel` helper function to manage tunnel creation and URL retrieval.
- Enhanced server startup logic to utilize the tunnel URL when available, improving accessibility for remote connections.
- Updated logging to provide feedback on tunnel status and URLs during server initialization.
* feat(inspector): enhance tunnel URL handling and update dependencies
- Added support for preserving the tunnel URL in navigation across inspector components.
- Introduced a new `tunnelUrl` state in the Inspector context to manage tunnel URL across the application.
- Updated various components to utilize the tunnel URL, ensuring seamless integration with the new functionality.
- Added `@radix-ui/react-popover` as a dependency in package.json for improved UI interactions.
- Updated pnpm-lock.yaml to reflect changes in dependency versions, including zod.
* feat(mcp): enhance widget integration and server handling
- Updated the CLI to fetch the MCP server from the new `/mcp` endpoint instead of `/inspector`.
- Improved tunnel establishment logging to include the new `/mcp` path.
- Enhanced HTML generation in the MCP server to replace relative paths for widget scripts and styles with absolute URLs.
- Added a script to the HTML head for dynamic file retrieval based on the server base URL, improving widget loading efficiency.
* disable tunnel in dev for now (since vite does not build assets
* fix(inspector): improve header handling in registerInspectorRoutes
- Updated header processing to exclude 'accept-encoding' to prevent compression issues.
- Added explicit request for uncompressed responses by setting 'Accept-Encoding' to 'identity'.
- Enhanced response header forwarding by omitting compression-related headers to ensure accurate body state representation.
* chore(typescript): version packages (canary)
* Feat/create mcp use app/templates (#390)
* readmes
* readme addition changeset
* chore(typescript): version packages (canary)
* format docs
---------
Co-authored-by: Enrico Toniato <2827496+tonxxd@users.noreply.github.com>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
* release(typescript): @mcp-use/inspector 0.4.7 + mcp-use 1.1.8 + create-mcp-use-app 0.4.8 + @mcp-use/cli 2.1.20
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
* Merge commit from fork
* fix: format
* feat(mcpagent): migrate to LangChain 1.0.0 and simplify agent methods
- Updated MCPAgent to utilize LangChain 1.0.0's `create_agent()` for improved agent instantiation.
- Introduced new methods `astream_simplified()` and `run_v2()` that leverage the built-in `astream()` for internal agent loop handling.
- Retained legacy methods `stream()` and `run()` for backward compatibility with manual execution.
- Enhanced documentation to reflect changes and provide clearer usage examples.
* feat(mcpagent): implement dynamic tool updates during agent execution
- Enhanced the MCPAgent to support dynamic tool updates when using server_manager mode.
- Implemented logic to check for tool changes before and during execution, allowing for immediate updates and safe restarts.
- Introduced a maximum restart limit to prevent infinite loops during tool updates.
- Updated documentation to reflect the new behavior and usage of dynamic tool management.
* feat(mcpagent): enhance agent execution with step tracking and middleware
- Introduced `ModelCallLimitMiddleware` to enforce a maximum number of model calls during agent execution.
- Updated the `_consume_and_return` method to return a tuple of the final result and the number of steps taken.
- Enhanced telemetry tracking to include steps taken and execution time for better performance insights.
- Simplified agent creation logic by integrating middleware directly into the `create_agent` function.
- Improved logging for agent execution details, including steps and tool usage.
* minor
* ruff
* format
---------
Co-authored-by: Luigi Pederzani <luigipederzani@gmail.com>
Co-authored-by: Enrico Toniato <2827496+tonxxd@users.noreply.github.com>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Vincenzo Reina <vincenzoreinaa05@gmail.com>
Ayaan Gazali