Per-job shared workspace (files) exposed as MCP tools for persona agents and the workflow engine
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":"persona-mcp-workspace","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.
> # ⚠️ Questo repository è stato migrato > > Lo sviluppo continua su GitHub: > **https://github.com/applica-software-guru/persona-mcp-workspace** > > Questa copia su Bitbucket è **congelata** e non riceve più commit, > release o pipeline. Aggiorna i tuoi remote: > > ```bash > git remote set-url origin git@github.com:applica-software-guru/persona-mcp-workspace.git > ``` > > Il pacchetto resta su PyPI (`persona-mcp-workspace`); l'immagine Docker > è su `ghcr.io/applica-software-guru/persona-mcp-workspace`. # persona-mcp-workspace Full-machine access exposed as MCP tools: `read`, `write`, `edit`, `bash`. This server is meant to be installed on a real machine so an agent can operate it remotely — the remote equivalent of a local coding agent's own tools, with no folder confinement. Paths are used exactly as given (absolute, or resolved against the server process's own working directory); `bash` runs with no forced cwd, inheriting the server process's own. ## Tools | tool | description | |---|---| | `read` | read a file — text with offset/limit, or images returned as image content a vision model can see | | `write` | create or overwrite a file, parents auto-created | | `edit` | precise text replacement — one or more disjoint edits per call | | `bash` | run a shell command, no working directory imposed — plain-text output (stdout+stderr merged; a JSON-object output also comes back as structuredContent), non-zero exit or timeout returned as a tool error; pi's exact result contract | | `skill` | load one skill's full instructions + bundled file paths | Any of these can be switched off, and their reach narrowed, from a config file — see [Permissions](#permissions). Listing, searching, deleting and moving files are **not** separate tools — `bash` covers them (`ls`, `grep`, `find`, `rm`, `mv`). One fewer surface to keep in sync with the agent-facing API, and the agent already knows how to use a shell. ## Images `read` detects images by magic bytes (never by extension)…
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.