"Target" matching MCP servers:

Enables ChatGPT in Chat mode to read and write local files, view the screen, and control the macOS desktop, with target locking and local permission controls.

Enables multiple agents sharing one working tree to claim, renew, release, and verify exclusive leases with strictly increasing fencing tokens, so a stale or evicted holder is refused at the write. Provides mediated writes that re-verify the token immediately before touching the target, with path confinement and no daemon.

Enables LLM agents to safely reclaim disk space by deleting build artifact directories like node_modules, .venv, and target, with strong guardrails to prevent accidental or malicious deletion.

Enables AI agents to analyze, compress, and verify PDFs while preserving text, vectors, and document structure, with configurable presets and target-size limits.

Enables agents to delegate bounded bulk file reads (returning only server-verified verbatim quotes) and boilerplate code generation from a reference file plus spec to the Cursor CLI running on its own separate quota, with the server itself writing the target file. It ships as a stdlib-only stdio MCP server with hash-pinned manifests, model policy, and WSL-first Windows support.

An MCP server providing an append-only, hash-chained evidence ledger for agent actions, where every record is a tamper-evident receipt cryptographically bound to all prior records and persisted as human-readable JSONL local state. It exposes tools to append records, verify chain integrity (pinpointing tampering), query records by actor/action/target/time, and fetch ledger stats—with no update or delete capabilities by design.