Easily manage, compose, and route MCP servers in Python projects
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"mcp-blender","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# mcp-blender Easily manage, compose, and route MCP (Model Context Protocol) servers in Python projects. ## Installation ```bash pip install mcp-blender ``` ## Usage ### Registry — manage servers ```python from mcp_blender import MCPServer, ServerTransport, Registry reg = Registry() reg.add(MCPServer( name="filesystem", command="npx", args=["-y", "@modelcontextprotocol/server-filesystem", "/home/user"], tools=["read_file", "write_file", "list_directory"], tags=["io"], )) reg.add(MCPServer( name="github", command="npx", args=["-y", "@modelcontextprotocol/server-github"], env={"GITHUB_TOKEN": "ghp_xxx"}, tools=["search_repositories", "create_issue"], tags=["code"], )) # Load from claude_desktop_config.json reg.load_claude_config("~/.claude/claude_desktop_config.json") # Or from YAML reg.load_yaml("mcp-servers.yaml") ``` ### Blender — profiles for different contexts ```python from mcp_blender import Blender blend = Blender() blend.register(filesystem_server) blend.register(github_server) blend.register(slack_server) blend.create_profile("coding", ["filesystem", "github"]) blend.create_profile("comms", ["slack"]) blend.activate("coding") # starts filesystem + github blend.activate("comms") # stops coding servers, starts slack ``` ### Router — route tool calls ```python from mcp_blender import Router router = Router(reg) server = router.resolve("read_file") # → filesystem server print(router.all_tools()) ``` ### CLI ```bash mcp-blender list servers.yaml mcp-blender export servers.yaml -o claude_desktop_config.json mcp-blender import claude_desktop_config.json -o servers.yaml ``` ## License MIT
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.