MCP transport for Mighty Mouse project verification and coding protocols
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":"mighty-mouse-mcp","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.
# Mighty Mouse MCP The MCP server exposes tools through the `mighty-mouse` server namespace: - `verify`: run tests, lint, build, and optional Git scope checks. - `protocol`: return the versioned low, medium, or high Mighty Mouse protocol. - `verify_and_record`: run verification and persist a content-free v2 Signal receipt. - `setup_workspace`: pin an exact local Ollama or host-supplied model identity and MCP execution profile without hand-writing config. - `recording_audit`: check that one exact host task receipt was recorded after it began. - `run`: adaptive routing and policy selection for a workspace task. - `agent_execute`: canonical coding execution with compute scaling support via `HostAdapter.solve`. - `swarm_execute`: execute Multi-Agent Swarm with canonical host provenance and isolated verification via `HostAdapter.solve_swarm`. - `policy_status`: inspect the active Champion policy and promotion status. - `policy_preview`: preview candidate policy selection without mutation. - `policy_pin`: pin an explicit policy for the workspace. - `policy_rollback`: roll back to the baseline Champion. - `compute_scaling_status`: inspect active compute scaling parameters. - `compute_scaling_preview`: preview compute scaling parameters without mutation. - `compute_scaling_pin`: pin exact compute scaling configuration for the workspace. Install both packages from a repository checkout: ```bash pip install . ./mcp ``` Run the stdio server: ```bash python -m mighty_mouse_mcp.server ``` Generic MCP configuration: ```json { "mcpServers": { "mighty-mouse": { "command": "python", "args": ["-m", "mighty_mouse_mcp.server"] } } } ``` The client presents these as `mighty-mouse/verify`, `mighty-mouse/protocol`, `mighty-mouse/setup_workspace`, `mighty-mouse/verify_and_record`, and `mighty-mouse/recording_audit` or equivalent namespaced forms. ## Cline learning adapter Use `setup_workspace` once per workspace, then use `verify_and_record` after every …
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.