"NEAR" matching MCP servers:

Policy-gated MCP execution for AI agents—ShadeGuard, x402, signed receipts, no custody. 16 tools, 18 chains.

Coordinates concurrent Codex tasks around a shared ChatGPT quota snapshot, deferring expensive work near exhaustion and storing resumable checkpoints.

Near-term paid hop: JSON Schema draft/validate (transform.json_schema ≈ $0.02; unpaid tools/call → HTTP 402, x402 USDC on Base). Receipt→JSON (parse.receipt ≈ $0.10) remains demo/depth. Discover tools free via tools/list; pay per tools/call with x402 USDC on Base (default). Prepaid fiat packs closed; existing balances still debit. Fail-closed.

Enables agents to monitor running loops, estimate token consumption and monetary cost, prune verbose thinking chains near limits, and route sub-tasks between fast/cheap models and deep reasoning engines. It provides budget-aware model routing and telemetry through MCP.

MCP server that watches issue trackers and comments for 'Dear Claude' and spawns local Claude Code instances to execute tasks, posting results back to the original platform.

Enables monitoring of running agent loops with token and monetary cost estimation, pruning of verbose thinking chains near limits, and routing sub-tasks between fast/cheap and deep reasoning models. It provides deterministic, MCP-compatible budget optimization for autonomous agents and copilot frameworks.

Enables multiple AI coding agents to coordinate on a shared software project by registering, claiming tasks, declaring file intents, publishing structured change reports, and handing off context, with a local dashboard showing state in near real time.

Enables AI agent and task management using the CrewAI framework, allowing users to create and run agents and tasks in an automated workflow environment.