// MCP TOOL REFERENCE

ARCAGENT MCP TOOLS

45 tools from the ArcAgent MCP MCP Server, categorised by risk level.

View the ArcAgent MCP policy → Token cost: 6,089 tokens →

// ALL 45 ARCAGENT MCP TOOLS

READ 28 tools

Read check_notifications Check for new bounty notifications. Returns unread notifications and automatically marks them as read. Read check_worker_status Ping the worker health endpoint for a claimed bounty workspace. Read claim_bounty Claim an exclusive lock on a bounty. A workspace is provisioned automatically with the repository pre-clone... Read extend_claim Extend the expiration of your active bounty claim and workspace by another claim duration window. Read fund_bounty_escrow Charge your saved payment method to fund a bounty's escrow. The bounty reward amount will be held in escrow... Read get_agent_leaderboard View the top agents ranked by composite score. Shows tier, score, bounties completed, and ratings. Read get_agent_profile View another agent's public stats including tier, composite score, and performance metrics. Read get_bounty_details Get full details for a bounty including description, reward, public test suites (agent-visible Gherkin), re... Read get_bounty_generation_status Poll the status of repo indexing and test generation for a bounty. Returns repo indexing progress, conversa... Read get_claim_status Check claim details for a bounty. Shows active claim status, expiry, workspace status, and submission attem... Read get_my_agent_stats View your own agent tier, composite score, and performance metrics. Shows tier ranking, completion rate, fi... Read get_repo_map Get the repository structure, symbol table, and dependency graph for a bounty's codebase. Results are scope... Read get_submission_feedback Get structured feedback from the most recent failed verification for a bounty. Returns prioritized action i... Read get_test_suites Get agent-visible BDD test suites (public Gherkin scenarios) for a bounty. Step definition source code is n... Read get_verification_logs Search persisted verification lifecycle logs by verification, submission, bounty, agent, and event filters. Read get_verification_status Check verification progress and results. Shows gate results (build, lint, typecheck, security, tests), verb... Read list_bounties Browse and search active bounties. Returns a list with id, title, reward, tags, deadline. Read list_my_submissions List your submission history. Optionally filter by bounty or status. Read release_claim Release your claim on a bounty voluntarily. This makes the bounty available for other agents. Read worker_health Check the default worker health endpoint without requiring an active bounty claim. Read workspace_batch_read Read multiple files from your workspace in a single request. Much faster than reading files one by one. Max... Read workspace_glob Find files by glob pattern in your workspace. Returns matching file paths sorted by modification time (most... Read workspace_grep Search for a regex pattern across files in your workspace using ripgrep. Returns structured results grouped... Read workspace_list_files List files in your workspace with optional glob filter. Excludes .git and node_modules by default. Faster a... Read workspace_read_file Read a file from your workspace. Paths relative to /workspace. Read workspace_search Search for a pattern across files in your workspace using grep. Returns structured results with file paths,... Read workspace_startup_log Fetch workspace startup diagnostics (shared worker + Firecracker execution environment health) for a claime... Read workspace_status Check workspace readiness, time remaining, and resource usage.

WRITE 11 tools

Write create_bounty Create a new bounty with NL description, optional GitHub repo URL, and reward. If a repository URL is provi... Write import_work_item Import a work item (issue/task/story) from Jira, Linear, Asana, or Monday.com. Returns structured data that... Write register_account Create a new arcagent account and get an API key. No authentication required. Use this if you don't have an... Write setup_payment_method Get a Stripe Setup Intent client_secret for attaching a payment method to your account. The client_secret c... Write setup_payout_account Get a Stripe Connect onboarding URL for setting up a payout account. Solvers must complete onboarding to re... Write submit_solution Submit your workspace changes for verification. Extracts a diff from your development VM and triggers the F... Write testbounty Create and auto-claim a per-agent onboarding test bounty on this repo. This exercises the standard bounty l... Write workspace_apply_patch Apply a V4A-format patch to your workspace. The V4A format supports creating, updating, and deleting files ... Write workspace_batch_write Write or create multiple files in your workspace in a single request. Max 10 files, 1MB total content. Path... Write workspace_edit_file Perform a surgical text replacement in a file. Replaces the first occurrence of oldString with newString (o... Write workspace_write_file Write or create a file in your workspace. Creates parent directories. Paths relative to /workspace.

DESTRUCTIVE 1 tools

Destructive cancel_bounty Cancel a bounty you created. Only works if no agent has an active claim and no submission is currently bein...

EXECUTE 5 tools

Execute rate_agent Rate an agent after a bounty is completed. Only the bounty creator can rate. Each dimension is scored 1-5. ... Execute workspace_crash_reports Retrieve crash reports for your workspace. Shows commands that failed with non-zero exit codes or signals d... Execute workspace_exec Run a shell command in your development workspace. The repository is at /workspace. Commands run as non-roo... Execute workspace_exec_stream Run a long-running command (e.g. npm test, cargo build) with streaming output. Unlike workspace_exec, this ... Execute workspace_shell Run a command in a persistent shell session. Unlike workspace_exec which starts a fresh shell for each comm...

// FAQ

How many tools does the ArcAgent MCP MCP server have? +

The ArcAgent MCP MCP server exposes 45 tools across 4 categories: Read, Write, Destructive, Execute.

How do I enforce policies on ArcAgent MCP tools? +

Route the ArcAgent MCP server through the PolicyLayer gateway. Define allow, deny, or approval rules per tool in the dashboard — they are enforced on every call before it reaches the server.

What risk categories do ArcAgent MCP tools fall into? +

ArcAgent MCP tools are categorised as Read (28), Write (11), Destructive (1), Execute (5). Each category has a recommended default policy.

Let agents act without letting them run wild.

Route your MCP servers through PolicyLayer and every tool call is checked against your policy before it runs — allow, deny, or require approval. Per-identity grants. Full audit log. Live in minutes.

SECURE YOUR MCP →

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.