MCP Registry

@iflow-mcp/uscensusbureau-us-census-bureau-data-api-mcp

fa04df03-11e1-557e-b389-e976ad78d4ad | Store v1.0.0
93/ 100
CRITICAL risk
Risk verdict
Do not install

Score-based assessment (critical risk, 93/100). An AI review is available in the AI review tab.

Analysis record

Analysed
2 months ago 26 August 2026
Version
v1.0.0
Artifact
SHA256 1d7496d9…8a0af5
Detail
Full list

Evidence ledger

Ranked by severity · findings with a source location link to the code viewer

332 findings

YARA Rule Matches

12 rules
SeverityRuleHitsFilesMetadata
LOWcredential env files 31
dist/helpers/citation.jsmcp-db/src/seeds/scripts/seed-database.tssrc/helpers/citation.ts +28 more
-
LOWpostinstall persistence mechanism 2
.github/copilot-instructions.mdmcp-db/data/topics.json
-
LOWUsingCommandLineArguments 2
mcp-db/src/seeds/scripts/seed-database.tsmcp-db/tests/seeds/scripts/seed-database.test.ts
-
LOWpostinstall file download 57
mcp-server/src/schema/validators.tsmcp-server/package.jsondist/schema/validators.js +54 more
-
LOWNoUseWeakRandom 3
mcp-db/tests/seeds/configs/summary-levels.config.test.tsmcp-db/tests/helpers/get-or-create-year.helper.test.tsmcp-db/tests/helpers/geography-years.helper.test.ts
-
LOWpostinstall obfuscation 3
mcp-db/tests/schema/geography.schema.test.tsmcp-db/src/schema/geography.schema.tsmcp-db/data/topics.json
-
LOWpostinstall crypto operations 9
mcp-db/tests/migrations/1752068025819_add-indexes-for-places-and-cache-tab.test.tsmcp-server/package-lock.jsonmcp-db/schema.sql +6 more
-
LOWpostinstall file manipulation 29
.github/workflows/build.ymlmcp-db/schema.sqlmcp-server/tests/helpers/citation.test.ts +26 more
-
LOWpostinstall environment access 53
mcp-db/src/seeds/configs/county-subdivision.config.tsdist/tools/fetch-aggregate-data.tool.jsmcp-db/tests/seeds/scripts/seed-database.test.ts +50 more
-
LOWpostinstall network communication 55
.github/copilot-instructions.md.github/workflows/build.ymlsrc/index.ts +52 more
-
LOWpostinstall registry modification 17
src/prompts/base.prompt.tsmcp-server/tests/prompts/base.prompt.test.tsmcp-server/tests/server.test.ts +14 more
-
LOWpostinstall system command 47
.github/workflows/build.ymlmcp-server/src/services/database.service.tsmcp-db/migrations/1754492912609_rename-geo-tables.ts +44 more
-

Finding Categories

6
Secrets
10
Network
76
IoC Indicators

YARA Rules Matched

12 rules(308 hits)
credential env files postinstall persistence mechanism UsingCommandLineArguments postinstall file download NoUseWeakRandom postinstall obfuscation postinstall crypto operations postinstall file manipulation postinstall environment access postinstall network communication postinstall registry modification postinstall system command

MCP Server Analysis

MCP servers expose tools and resources to AI assistants. Unlike browser extensions, they run as standalone processes with direct system access. Tool definitions are analyzed for prompt injection, data exfiltration, and tool poisoning patterns.

AI Security Report

AI Security Review

Evidence context: threat category none; evidence quality weak.

This package presents a Critical risk score of 100, primarily driven by an exceptionally high volume of IoC findings (720) and generic malware-signature matches (308). However, a detailed review reveals these are almost certainly false positives characteristic of bundled node_modules rather than malicious code.

Tool Poisoning Assessment: The findings summary explicitly reports tool-poisoning: 0. There are no indications of hidden AI directives or description manipulation. The package appears to be a standard data integration tool without the 'mind-control' mechanics seen in actual MCP poisoning attacks.

Credential & Network Scope: There are no reported secrets or specific credential-access findings targeting sensitive files (e.g., .ssh, .aws). The 10 network findings are likely HTTP clients for the Census API. Without exfiltration destinations or specific secret harvesting, this falls within normal operational boundaries.

False Positive Drivers: The IoC count (720) is the primary risk inflator. In MCP packages, this frequently stems from IPv6 fragments (::), loopback addresses (127.0.0.1), or CDN domains found inside minified JavaScript dependencies. The 308 malware-signature hits suggest inclusion of libraries that trigger overly broad YARA rules (e.g., matching generic hex patterns or config files). These findings, while voluminous, do not indicate an active threat in this context.

Key Reasons

  • Zero tool-poisoning findings despite critical risk label
  • Massive IoC count (720) consistent with bundled dependency noise, not real indicators
  • No secret/credential findings targeting specific files
  • YARA malware signatures likely triggered by generic code patterns in dependencies

False Positive Considerations

  • High IoC volume from bundled node_modules (dist files)
  • Broad YARA malware-signature rules matching generic patterns
  • Risk score inflation from non-specific findings

Reviewed 2026-04-12; recommended action: suppress false positive; model confidence 70%.

Source Code Viewer

Source Code Not Available

Source code is not available for this version of the extension.

About This Extension

[![License: CC0-1.0](https://img.shields.io/badge/License-CC0%201.0-lightgrey.svg)](https://github.com/uscensusbureau/us-census-bureau-data-api-mcp/blob/main/LICENSE) [![MCP Project Build](https://github.com/uscensusbureau/us-census-bureau-data-api-mcp/ac

Frequently Asked Questions