MCP Agentic Server
UnclaimedTurn Claude, ChatGPT, and any LLM into a safe, bloat-free Autonomous Coding Agent with semantic navigation and worktree sandboxing.
Set up this server
01 / Choose your client
02 / Before you connect
Authentication is not specified. Check the project instructions before connecting.
Project instructions03 / Add the configuration
claude mcp add --transport stdio 'mcp-agentic-server' -- 'npx' '-y' 'mcp-agentic-server@latest' 'stdio'04 / Check it in your client
Open your client’s MCP settings and confirm the server connects and lists its tools. A copied configuration does not confirm a working connection.
More in AI & ML
Browse the full directoryUnclaimed listing
Is this your MCP server?
This listing was auto-indexed from the public record. Claim it to edit the page, set compatibility and unlock growth tools. Takes under two minutes.
Claim this serverSecurity profile
Claimed and verified servers get a weekly static scan that shows what the code can reach: external services, environment variables, shell commands, agent configuration folders, plus any dependencies with known advisories. Claim this listing to get one. How the security profile works
24 of 24 tools
Documented tools (24)
From project documentation. A server handshake does not verify each tool’s description or behavior.
agentic_doctor
Diagnose Node, package managers, Git and native SQLite availability.
bash
Fallback for shell interactions that have no typed tool; prefer runpackagescript for package scripts and the Git tools for Git.
changed_files_summary
Fast Git status and diff abstraction.
checkpoint_
Save, restore, list, or delete snapshots.
context_budget
Estimate token count for files.
edit
Targeted string replacements.
edit_dry_run
Preview edits without writing.
expand_compressed_block
Expand omitted blocks from readcompressed.
file_dependencies
Inward and outward dependency map.
open_workspace
Opens a project. Supports mode="checkout" or mode="worktree".
project_bootstrap
Scans package managers, monorepo bounds, and base dependencies.
read
Hardened file reader with startLine, endLine, offset, limit.
read_many
Read multiple files at once.
risk_assess_command
Preview policy assessment before bash.
semantic_pack
Compact goal-relevant summary with token budget.
suggest_checks
Advisory planner returning a deterministic VerificationPlan.
task_context
Computes a RiskProfile (risk level, score, blast radius) from focused paths.
token_audit
Analyze token usage across files read.
tournament_
Autonomous evaluation and judgment of changes.
tree
Directory tree visualization.
workspace_summary
Compact architectural summary of the workspace.
worktree_
Manage isolated git worktrees (create, list, sync, teardown).
worktree_install_deps
Install dependencies in a managed worktree; use verify: true to load native bindings.
write
Create or overwrite files.
Tool change history
FAQ
Questions about MCP Agentic Server MCP Server
- How do I connect MCP Agentic Server MCP Server to Claude?
- Run `claude mcp add mcp-agentic-server -- npx -y mcp-agentic-server@latest stdio` in Claude Code, or add the same command and arguments under mcpServers in Cursor's mcp.json or Claude Desktop's claude_desktop_config.json, then restart the client. The blocks above are ready to paste.
- Is MCP Agentic Server MCP Server free?
- The listed licence is MIT. Check the upstream terms for permitted use and commercial requirements; a public repository does not by itself mean the software is free or open source. Connected APIs and hosted services may have separate charges.
- What can MCP Agentic Server MCP Server do?
- MCP Agentic Server MCP Server documents 24 tools to the agent, including agentic_doctor, bash, changed_files_summary. The descriptions above come from project documentation. A live handshake does not test individual tool behavior.