# Cost Guard MCP (pypi · cost-guard-mcp)

Pre-flight query cost and result-size guardrails for AI agents on BigQuery, Snowflake, Databricks

- Trust score: 69/100 (medium)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-20

## Components

- pypi · `cost-guard-mcp`: 69/100 (this document), [markdown](https://verifymcp.io/servers/mcpsmiths-cost-guard-mcp/cost-guard-mcp.md), [page](https://verifymcp.io/servers/mcpsmiths-cost-guard-mcp/cost-guard-mcp)

## Channel facts

- Registry: `pypi`
- Package: `cost-guard-mcp`
- Version: `0.3.0`
- Transport: `stdio`

## Trust breakdown

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. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-09-20.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs hatchling.build at install time, a recognised native-build step with no shell scripting around it.
  - 5 of 77 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 35/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - License check failed: no license is declared.
  - Actively maintained (last published 1 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 69/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 493 tokens (~123/item across 4 items; 4 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 71/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 4 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 4 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the Cost Guard MCP server?

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

### Claude

```bash
claude mcp add mcpsmiths-cost-guard-mcp -- uvx cost-guard-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "mcpsmiths-cost-guard-mcp": {
      "command": "uvx",
      "args": [
        "cost-guard-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "mcpsmiths-cost-guard-mcp": {
      "command": "uvx",
      "args": [
        "cost-guard-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add mcpsmiths-cost-guard-mcp -- uvx cost-guard-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "mcpsmiths-cost-guard-mcp": {
      "type": "local",
      "command": [
        "uvx",
        "cost-guard-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add mcpsmiths-cost-guard-mcp --command uvx --arg cost-guard-mcp
```

### Hermes

```yaml
mcp_servers:
  mcpsmiths-cost-guard-mcp:
    command: "uvx"
    args: ["cost-guard-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "mcpsmiths-cost-guard-mcp": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "cost-guard-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add mcpsmiths-cost-guard-mcp -t stdio -c uvx -a cost-guard-mcp
```

### Other

```json
{
  "mcpServers": {
    "mcpsmiths-cost-guard-mcp": {
      "command": "uvx",
      "args": [
        "cost-guard-mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-09-20 (score 69, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-18 (score 68, +1)

- [functional] Package version: 0.2.0 → 0.3.0

### 2026-09-17 (score 67, 0)

- [security regression] Stability: 0.13 → unverified
- [security regression] Tool safety: pass → unverified
- [functional regression] Schema quality: 92 → 123
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional] First check of Schema quality: unverified
- [functional] Package version: 0.1.1 → 0.2.0

### 2026-09-15 (score 67, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-14 (score 66, +1)

- [security regression] Malware scan: pass → unverified
- [functional improvement] Stability: unverified → 0.07
- [functional improvement] Security disclosure: fail → pass
- [functional] Package version: 0.1.0 → 0.1.1

### 2026-09-13 (score 65, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-09-12 (score 50)

First indexed and scored.

## MCP tools (4)

### `check_credentials` (~72 tokens)

Verify credentials/connectivity for an engine without running any real query or
dry-run estimate. Call this once after configuring a new engine (or when a real tool
call fails) to get a fast, clear yes/no signal instead of debugging via trial queries.

Input parameters:

- `engine` (string, required)
- `warehouse`

Output parameters:

- `detail` (string)
- `engine` (string)
- `ok` (boolean)

### `describe_engine_capabilities` (~61 tokens)

Declare which cost signals are exact vs. approximate for the given warehouse engine.

Call this before estimate_query_cost or run_query_bounded to understand how much to
trust the accuracy_tier on their responses for this engine.

Input parameters:

- `engine` (string, required)

Output parameters:

- `default_accuracy_tier`
- `engine` (string)
- `known_gaps` (array)
- `supports_dollar_estimate` (boolean)
- `supports_precise_bytes` (boolean)

### `estimate_query_cost` (~174 tokens)

Estimate the cost of a SQL query before running it. ALWAYS call this before running
an expensive-looking query. The response's accuracy_tier tells you how much to trust
the number: PRECISE (exact), UPPER_BOUND (real cap, may overstate), HEURISTIC (rough).

warehouse_size (Snowflake/Databricks only, e.g. "SMALL", "X-Large") and edition
(Snowflake only, e.g. "enterprise") default to the smallest/standard tier if omitted —
set them to match the warehouse you actually run this query on, or the dollar figure
will understate cost on a larger warehouse.

Input parameters:

- `edition`
- `engine` (string, required)
- `sql` (string, required)
- `warehouse`
- `warehouse_size`

Output parameters:

- `accuracy_tier`
- `caveats` (array)
- `currency` (string)
- `engine` (string)
- `estimated_bytes`
- `estimated_cost_usd`

### `run_query_bounded` (~186 tokens)

Run a query only if its pre-flight cost estimate is within your given bounds; refuses
otherwise (check result.status — "refused" means it did NOT run and result.hint explains
why). NOTE: unlike estimate_query_cost, a successful call here has a real monetary/quota
side effect — don't call this repeatedly without inspecting the result of each call.

warehouse_size/edition (see estimate_query_cost) default to the smallest/standard tier
if omitted - set them to match the warehouse you actually run on, since max_estimated_cost_usd
is checked against the estimate they produce.

Input parameters:

- `edition`
- `engine` (string, required)
- `max_bytes_billed`
- `max_estimated_cost_usd`
- `max_rows`
- `sql` (string, required)
- `warehouse`
- `warehouse_size`

Output parameters:

- `estimate`
- `hint`
- `reason`
- `row_count`
- `rows`
- `status` (string)

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/mcpsmiths-cost-guard-mcp/cost-guard-mcp#diagnostics

## Score history

- 2026-09-20: 69
- 2026-09-19: 68
- 2026-09-18: 68
- 2026-09-17: 67
- 2026-09-16: 67
- 2026-09-15: 67
- 2026-09-14: 66
- 2026-09-13: 65
- 2026-09-12: 50

## Common questions

### What is the Cost Guard MCP server?

Cost Guard MCP is listed in the public MCP registry as io.github.mcpsmiths/cost-guard-mcp. Pre-flight query cost and result-size guardrails for AI agents on BigQuery, Snowflake, Databricks. This page covers its PyPI package (cost-guard-mcp).

### Is the Cost Guard MCP server safe to use?

Cost Guard MCP scores 69 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 Cost Guard MCP server expose?

Cost Guard MCP exposes 4 tools: check_credentials, describe_engine_capabilities, estimate_query_cost, run_query_bounded. Their descriptions and schemas cost roughly 493 tokens of context every time the server is loaded.

### Is the Cost Guard MCP server still maintained?

Cost Guard 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.

## Links

- PyPI project: https://pypi.org/project/cost-guard-mcp/
- Socket report: https://socket.dev/pypi/package/cost-guard-mcp
- Repository: https://github.com/mcpsmiths/cost-guard-mcp
- Changelog RSS feed: https://verifymcp.io/servers/mcpsmiths-cost-guard-mcp/cost-guard-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/mcpsmiths-cost-guard-mcp/cost-guard-mcp.json
- HTML version of this page: https://verifymcp.io/servers/mcpsmiths-cost-guard-mcp/cost-guard-mcp