Skip to content
Agentmart
Submit a tool

Bollard MCP

An AI-powered, safe database access gateway built on the Model Context Protocol (MCP).

Connector by ImDeepaksingh · GitHub account verified by the MCP Registry

IndexedAGPL-3.0Local (stdio)
Write a review

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/imdeepaksingh-bollard-mcp

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

An AI-powered, safe database access gateway built on the Model Context Protocol (MCP).

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.

Tools
7 read · 3 write · 0 delete · 4 not yet classified
Secrets
None asked for
Install scripts
Not scanned yet
Runs as
Python package

Tools by what they do 14

Read from the source code; the running server may list different tools.

Read 7 · Look things up without changing anything.

  • describe_table
  • get_corrections
  • get_query_history
  • get_sample_data
  • list_connections
  • list_tables
  • preview_query

Write 3 · Create, change, send or run things.

  • disconnect
  • execute_query
  • reconnect_saved

Not yet classified 4 · We could not tell from the name and description.

  • connect_database
  • log_correction
  • profile_table
  • refresh_schema

Tools (14)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

  • connect_database

    Connect to a database. Args: connection_string: Full database URL. PostgreSQL: postgresql://user:pass@host:5432/dbname MySQL: mysql://user:pass@host:3306/dbname SQLite: sqlite:///path/to/file.db MSSQL: mssql://user:pass@host:1433/dbname alias: Short name for this connection (e.g., 'prod', 'staging'). mode: Permission mode — 'read_only' | 'read_write' | 'admin'. Default: 'read_only' (safest). max_rows: Maximum rows returned by SELECT queries (auto-LIMIT). forbidden_tables: Tables to block access to. Supports wildcards: …

  • describe_table

    Show full column definitions, types, constraints, and indexes for a table. Includes: column names, data types, nullable, primary key, unique, foreign keys. The editor AI reads this to understand the exact schema before generating queries. Args: connection: Database alias. table_name: Table to describe (exact name, case-sensitive).

  • disconnect

    Close connection cleanly.

  • execute_query

    Execute a SQL query through the risk-tiered safety pipeline. Risk tiers: LOW (SELECT) → auto-execute, no gate. MEDIUM (write < 5 rows) → OS PIN required. HIGH (write >= 5 rows) → OS PIN + type "confirm update N rows". CRITICAL (ALTER TABLE) → OS PIN + review suggested reversal. EXTREME (DROP / TRUNCATE) → blocked unless mode='admin'. Output modes (override connection default): 'raw' → Full raw rows always. 'smart' → Sample + stats for large results (default). 'analytics' → Zero rows, stats only. Args: connection: Database…

  • get_corrections
  • get_query_history

    Return recent query history for a connection. Useful for the editor AI to understand what has been executed recently, especially when the user says "run that again" or "fix the last query." Args: connection: Database alias. last_n: Number of recent queries to return (max 50, default 10).

  • get_sample_data

    Preview a few rows from a table to understand its data shape. Useful for the editor AI to understand the actual values in the database before generating queries (e.g., what status values exist, date formats, etc.) Args: connection: Database alias. table_name: Table to sample. limit: Number of rows to return (max 25, default 5).

  • list_connections
  • list_tables

    List all tables in the connected database with row counts and sizes. The editor AI uses this to understand the database structure before generating queries. Schema is served from cache when available. Args: connection: Database alias (from connect_database).

  • log_correction

    Log a query correction for future AI context. When the editor AI generates a wrong query and the user corrects it, log the correction here. Bollard persists it and exposes it via the bollard://corrections/{alias} MCP Resource, so the AI automatically learns from past mistakes without the user repeating themselves. Args: connection: Database alias. original_query: The incorrect SQL that was generated. corrected_query: The correct SQL (or empty if just a note). note: Plain English explanation of what was wrong and why. Examples: - "Exclude test accounts: ema…

  • preview_query

    Dry-run a query through the full safety + intent pipeline. Returns: - Safety verdict (SAFE / BLOCKED with reason) - Intent analysis (interpreted intent, assumed filters, ambiguity warnings) - EXPLAIN cost estimate (PostgreSQL only) - Final SQL with auto-LIMIT applied For bare SELECT * queries on large tables, Bollard will automatically redirect to profile_table to give the AI richer context with fewer tokens. The editor AI should call this before execute_query for any non-trivial query. Args: connection: Database alias (from connect_database). sql: SQL statement to preview.

  • profile_table

    Generate a statistical profile of a database table. All aggregation is performed directly in the database via SQL queries. No rows are transferred to local memory. Returns a compact Markdown summary suitable for AI context (< 150 tokens overhead per column). Includes for every column: - Row count and null percentage - Distinct value count - Min / Max / Avg (numeric and date columns) - Top-5 value distribution for categorical columns (<= 100 distinct values) Args: connection: Database alias (from connect_database). table_name: Name of the table to profile.

  • reconnect_saved

    Reconnect to a previously saved connection from the OS Keyring. Args: alias: The saved connection alias to restore.

  • refresh_schema

    Force a schema cache refresh for a connection. Call this after CREATE TABLE, ALTER TABLE, or any DDL operation to ensure the AI has up-to-date schema context. Args: connection: Database alias.

Signals

Weekly downloads
39
Last release
Jul 19, 2026 (3 months ago)
Last package publish
Jul 19, 2026 (3 months ago)

From the package registry.

Details

Registry name
io.github.ImDeepaksingh/bollard-mcp
Version
0.1.4
Auth
No auth
Packages
pypi bollard-mcp
License
AGPL-3.0
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Cite this page

Bollard MCP. Agent Mart. https://agentmart.dev/connectors/imdeepaksingh-bollard-mcp (last updated 2026-10-24)