// SCAN REPORT

Vigentic MCP

37 tools. 24 can modify or destroy data without limits.

2 destructive tools with no built-in limits. Policy required.

Last updated: 3 Jul 2026

24 can modify or destroy data

13 read-only

37 tools total

Community server · catalogue entry verified 03/07/2026

How to control Vigentic MCP ↓

TOOL MAP

What Vigentic MCP exposes to your agents

Read (13) Write / Execute (22) Destructive / Financial (2)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Vigentic MCP tools

Destructive · High delete_file This tool irreversibly deletes files from disk, making it a Destructive action. Destructive · High discard_buffer_changes This tool irreversibly discards unsaved changes in a buffer. Execute · Medium organize_imports The tool actively runs an LSP mutation operation that reorganizes import statements in a buffer. Execute · Medium verify_checkpoint While the tool starts with validation (a Read-like operation), it explicitly runs 'ordered verification commands', which constitutes executing external operations.

24 of Vigentic MCP's 37 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Vigentic MCP

PolicyLayer is an MCP gateway — it sits between your AI agents and Vigentic MCP, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "delete_file": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "apply_edit_batch": {
    "limits": [
      {
        "counter": "apply_edit_batch_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "definition": {
    "limits": [
      {
        "counter": "definition_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Vigentic MCP — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON VIGENTIC →

Instant setup, no code required.

FULL CATALOGUE

All 37 Vigentic MCP tools

DESTRUCTIVE 2 tools

Destructive delete_file Delete a file from disk and close any matching open buffers first. Destructive discard_buffer_changes Discard unsaved changes in an open buffer and reload its on-disk contents.

EXECUTE 3 tools

Execute organize_imports Run a TypeScript or JavaScript organize-imports mutation without saving the target buffer. useLatestChangedTic Execute verify_checkpoint Validate a checkpoint against disk state, then run ordered verification commands only if the checkpoint is sti Execute verify_workspace Combine diagnostics, command execution, and optional repo-hygiene checks into one verification summary. Comman

WRITE 19 tools

Write apply_edit_batch Apply multiple ordered edits against one target buffer with one initial changed-tick check. useLatestChangedTi Write apply_hunk Apply one unified diff hunk to the current buffer or an optional file path. useLatestChangedTick is current-bu Write apply_multi_file_batch Preview or apply ordered explicit-target edit batches across multiple files, with optional checkpoint saves fo Write claim_files Claim explicit file ownership for an agent before implementation begins. Write create_checkpoint Create a saved-state checkpoint for explicit files without saving buffers implicitly. Write create_directory Create a directory on disk. Write create_file Create a file on disk. Parent directories must already exist. Write create_files Create or overwrite multiple files in order. Parent directories must already exist for every entry unless crea Write format_buffer Format the current buffer or an explicit target through the headless Neovim runtime without saving. useLatestC Write move_file Move or rename a file on disk, reusing an open source buffer when possible. Write release_files Release explicit file ownership for an agent after handoff or completion. Write replace_buffer Replace the entire current Neovim buffer or explicit target buffer as a fallback full-buffer rewrite. useLates Write replace_exact Replace one exact snippet in the current buffer or an optional file path. useLatestChangedTick is current-buff Write replace_lines Replace an inclusive 0-based line range in the current buffer or an explicit buffer target. useLatestChangedTi Write save_all_buffers Save every dirty file-backed open buffer and report saved, skipped, and failed entries. Write save_buffer Save the current Neovim buffer or an explicit open buffer target to disk. Write save_files Save only the requested open file buffers and record fresh saved-state metadata. Write setup_agents Create or update a repo-local Vigentic MCP contract in AGENTS.md and scaffold docs/agent-usage.md when it is m Write suggest_edit_retry Suggest the next edit action after a failed edit attempt, using the failure text, attempted args, and an optio

READ 13 tools

Read definition Resolve the definition at a file position. Read find_files Find files in the workspace without dropping to the shell. Read get_buffer A warmed Neovim session compares an in-process Read get_diagnostics A warmed stdio MCP client measures connect cost plus repeated reads against the new resource surface, with com Read get_dirty_owned_files List dirty open buffers currently owned by an agent, with optional buffer-vs-disk diffs. Read get_file_owners Return current file ownership and saved-state metadata for explicit paths. Read list_open_buffers List file-backed open buffers and whether they are dirty or current. Read open_file Open an existing file inside the headless Neovim instance. Read references Resolve references at a file position. Read reload_buffer Reload a clean open buffer from disk without discarding unsaved changes. Read search_text Search on-disk workspace text and return structured matches; unsaved Neovim buffer changes are not included. Read workspace_hygiene Summarize git working tree state and common generated artifact leaks under a root. Read workspace_status Show repo-scoped open buffers, dirty state, current buffer, and changed ticks in one response.

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Vigentic MCP

Can an AI agent delete data through the Vigentic MCP server? +

Yes. The Vigentic MCP server exposes 2 destructive tools including delete_file, discard_buffer_changes. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Vigentic MCP? +

The Vigentic MCP server has 19 write tools including apply_edit_batch, apply_hunk, apply_multi_file_batch. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Vigentic MCP.

How many tools does the Vigentic MCP server expose? +

37 tools across 4 categories: Destructive, Execute, Read, Write. 13 are read-only. 24 can modify, create, or delete data.

How do I enforce a policy on Vigentic MCP? +

Register the Vigentic MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Vigentic MCP tool call.

Deterministic rules across all 37 Vigentic MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON VIGENTIC →

Instant setup, no code required.

37 Vigentic MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.