Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Bollard MCP

PYPI · BOLLARD-MCP · SCANNED SEP 20

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

Available components

0 this week 78 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security100
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • Runs hatchling.build at install time, a recognised native-build step with no shell scripting around it. View diagnostics → Pass
  • 4 of 46 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency19
Schema Quality & AI Usability84
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 1861 tokens (~124/item across 15 items; 14 tools + 1 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management87
  • Stability observed for 26 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
  • Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety75
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "execute_query" implies "execute" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
  • An AI judge read all 16 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a current MCP spec version (2026-07-28).Pass
Install

How do I install the Bollard MCP server?

Bollard MCP runs locally as a PyPI package, launched with uvx bollard-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

pypi · bollard-mcp

# add to Claude Code
claude mcp add imdeepaksingh-bollard-mcp -- uvx bollard-mcp
// .cursor/mcp.json
{
  "mcpServers": {
    "imdeepaksingh-bollard-mcp": {
      "command": "uvx",
      "args": [
        "bollard-mcp"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "imdeepaksingh-bollard-mcp": {
      "command": "uvx",
      "args": [
        "bollard-mcp"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add imdeepaksingh-bollard-mcp -- uvx bollard-mcp
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "imdeepaksingh-bollard-mcp": {
      "type": "local",
      "command": [
        "uvx",
        "bollard-mcp"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add imdeepaksingh-bollard-mcp --command uvx --arg bollard-mcp
# ~/.hermes/config.yaml
mcp_servers:
  imdeepaksingh-bollard-mcp:
    command: "uvx"
    args: ["bollard-mcp"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "imdeepaksingh-bollard-mcp": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "bollard-mcp"
      ]
    }
  }
}
# add to Vellum
assistant mcp add imdeepaksingh-bollard-mcp -t stdio -c uvx -a bollard-mcp
// mcp.json
{
  "mcpServers": {
    "imdeepaksingh-bollard-mcp": {
      "command": "uvx",
      "args": [
        "bollard-mcp"
      ]
    }
  }
}
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 20 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

  • 18 Sept 26 −2
    • Stability: pass → 0.80 functional
  • 17 Sept 26 0
    • Stability: 0.97 → pass security
  • 16 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

  • 15 Sept 26 +15
    • Malware scan: unverified → pass security
  • 14 Sept 26 −15
    • Malware scan: pass → unverified security
  • 13 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

  • 12 Sept 26 +15
    • Malware scan: unverified → pass security
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 20 Sept 2026 · Analysed pypi/bollard-mcp@0.1.4

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem pypi

Background: How many MCP packages publish verified provenance →

Install scripts 1 script
Hook Tier Command
build_backend allowlisted hatchling.build

Background: Why install scripts are a supply-chain risk →

Dependencies 46 packages
Packages resolved 46
Stale 4
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 14 exposed · ~1,345 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
connect_database ~293

Connect to a database.

NameTypeReqDescription
aliasstringyesShort name for this connection (e.g., 'prod', 'staging').
connection_stringstringyesFull 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/dbn…
forbidden_tablesTables to block access to. Supports wildcards: '*.passwords', 'auth.*', 'users_secrets'
max_rowsintegerMaximum rows returned by SELECT queries (auto-LIMIT).
modestringPermission mode — 'read_only' | 'read_write' | 'admin'. Default: 'read_only' (safest).
output_modestringControls how query results are returned to the AI. 'smart' (default) — Full results for small queries; 10-row sample + column stats for large ones. 'raw' — Always return full ra…
save_credentialbooleanIf True, saves to OS Keyring for future sessions.
NameTypeReqDescription
resultstringyes

No examples provided.

describe_table ~81

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.

NameTypeReqDescription
connectionstringyesDatabase alias.
table_namestringyesTable to describe (exact name, case-sensitive).
NameTypeReqDescription
resultstringyes

No examples provided.

disconnect ~24

Disconnect from a database.

NameTypeReqDescription
aliasstringyesThe connection alias to disconnect.
NameTypeReqDescription
resultstringyes

No examples provided.

execute_query ~102

Execute a SQL query through the risk-tiered safety pipeline.

NameTypeReqDescription
confirmation_phraseRequired for HIGH risk — typed phrase e.g. "confirm update 12000 rows".
confirmedbooleanRequired for write operations.
connectionstringyesDatabase alias (from connect_database).
output_modeOverride the connection's default output mode.
pinOS PIN for write authorization.
sqlstringyesSQL statement to execute.
NameTypeReqDescription
resultstringyes

No examples provided.

get_corrections ~56

Return all logged corrections for a connection. The editor AI reads this via the bollard://corrections/{alias} MCP Resource automatically. Call this tool directly to inspect them.

NameTypeReqDescription
connectionstringyesDatabase alias.
NameTypeReqDescription
resultstringyes

No examples provided.

get_query_history ~78

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."

NameTypeReqDescription
connectionstringyesDatabase alias.
last_nintegerNumber of recent queries to return (max 50, default 10).
NameTypeReqDescription
resultstringyes

No examples provided.

get_sample_data ~93

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.)

NameTypeReqDescription
connectionstringyesDatabase alias.
limitintegerNumber of rows to return (max 25, default 5).
table_namestringyesTable to sample.
NameTypeReqDescription
resultstringyes

No examples provided.

list_connections ~27

List all currently active database connections. Returns alias, dialect, permission mode, and connection time.

Input schema present but exposes no named parameters.

NameTypeReqDescription
resultstringyes

No examples provided.

list_tables ~57

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.

NameTypeReqDescription
connectionstringyesDatabase alias (from connect_database).
NameTypeReqDescription
resultstringyes

No examples provided.

log_correction ~183

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.

NameTypeReqDescription
connectionstringyesDatabase alias.
corrected_querystringyesThe correct SQL (or empty if just a note).
notestringyesPlain English explanation of what was wrong and why. Examples: - "Exclude test accounts: email LIKE '%@test.com%'" - "Use created_at, not signup_date — signup_date is deprecated" - "active us…
original_querystringyesThe incorrect SQL that was generated.
NameTypeReqDescription
resultstringyes

No examples provided.

preview_query ~137

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.

NameTypeReqDescription
connectionstringyesDatabase alias (from connect_database).
sqlstringyesSQL statement to preview.
NameTypeReqDescription
resultstringyes

No examples provided.

profile_table ~128

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)

NameTypeReqDescription
connectionstringyesDatabase alias (from connect_database).
table_namestringyesName of the table to profile.
NameTypeReqDescription
resultstringyes

No examples provided.

reconnect_saved ~34

Reconnect to a previously saved connection from the OS Keyring.

NameTypeReqDescription
aliasstringyesThe saved connection alias to restore.
NameTypeReqDescription
resultstringyes

No examples provided.

refresh_schema ~52

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.

NameTypeReqDescription
connectionstringyesDatabase alias.
NameTypeReqDescription
resultstringyes

No examples provided.

Common questions

What is the Bollard MCP server?

Bollard MCP is listed in the public MCP registry as io.github.ImDeepaksingh/bollard-mcp. An AI-powered, safe database access gateway built on the Model Context Protocol (MCP). This page covers its PyPI package (bollard-mcp).

Is the Bollard MCP server safe to use?

Bollard MCP scores 78 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the Bollard MCP server expose?

Bollard MCP exposes 14 tools: connect_database, disconnect, list_connections, reconnect_saved, list_tables, and 9 more. Their descriptions and schemas cost roughly 1,345 tokens of context every time the server is loaded.

Is the Bollard MCP server still maintained?

Bollard MCP is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the Bollard MCP server under?

Bollard MCP declares the AGPL-3.0-only licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.