Skip to main content
Glama

Server Details

Scan GitHub-hosted AI skills for vulnerabilities: prompt injection, malware, OWASP LLM Top 10.

Status
Healthy
Last Tested
Transport
Streamable HTTP
URL
Repository
securityscan-api/securityscan-api
GitHub Stars
0
Server Listing
securityscan

Glama MCP Gateway

Connect through Glama MCP Gateway for full control over tool access and complete visibility into every call.

MCP client
Glama
MCP server

Full call logging

Every tool call is logged with complete inputs and outputs, so you can debug issues and audit what your agents are doing.

Tool access control

Enable or disable individual tools per connector, so you decide what your agents can and cannot do.

Managed credentials

Glama handles OAuth flows, token storage, and automatic rotation, so credentials never expire on your clients.

Usage analytics

See which tools your agents call, how often, and when, so you can understand usage patterns and catch anomalies.

100% free. Your data is private.

Tool Definition Quality

Score is being calculated. Check back soon.

Available Tools

3 tools
check_certificationAInspect
Check if a skill has been certified as safe.

Certification indicates the skill has been scanned, reviewed,
and approved by a human administrator. Certified skills have
a cryptographic hash that can be verified. Does not consume scan credits.

Args:
    skill_url: The skill URL to check certification for

Returns:
    CertificationResult indicating if the skill is certified,
    along with certification details if available.

Example:
    check_certification("https://github.com/anthropics/anthropic-cookbook")
ParametersJSON Schema
NameRequiredDescriptionDefault
skill_urlYes

Output Schema

ParametersJSON Schema
NameRequiredDescription
scoreNo
cert_hashNo
skill_urlYes
certified_atNo
is_certifiedYes
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full disclosure burden effectively. It explains certification semantics (human-reviewed, cryptographic hash verification) and cost behavior (no scan credits consumed). It also identifies the return type (CertificationResult), though it could mention error cases like invalid URLs.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description uses a structured format (initial statement, Args, Returns, Example) that is appropriately front-loaded. Information density is high with minimal redundancy, though the certification process explanation could be slightly more concise.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a single-parameter tool with an output schema, the description is complete. It explains what CertificationResult contains (certification status and details) without needing to replicate the full output schema, and adequately covers the certification domain concept.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Given 0% schema description coverage, the description compensates well by documenting the skill_url parameter in the Args section ('The skill URL to check certification for') and providing a concrete example value ('https://github.com/anthropics/anthropic-cookbook').

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool 'Check[s] if a skill has been certified as safe' with specific verb and resource. It implicitly distinguishes from sibling scan_skill by noting 'Does not consume scan credits,' though it doesn't explicitly contrast with get_report.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit behavioral guidance with 'Does not consume scan credits,' which strongly implies when to use this (for cost-free verification) versus scan_skill. However, it lacks explicit 'when-not-to-use' statements or direct comparisons to get_report.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_reportAInspect
Get the public security report for a skill.

Returns the most recent scan results and certification status.
This is useful to check if a skill has been previously scanned
without triggering a new scan. Does not consume scan credits.

Args:
    skill_url: The skill URL to get the report for

Returns:
    ReportResult with score, certification status, and issues summary.
    Returns error if no report exists for this URL.

Example:
    get_report("https://github.com/jlowin/fastmcp")
ParametersJSON Schema
NameRequiredDescriptionDefault
skill_urlYes

Output Schema

ParametersJSON Schema
NameRequiredDescription
scoreYes
cert_hashNo
certifiedYes
skill_urlYes
certified_atNo
issues_summaryYesCount of issues by severity
recommendationYes
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description carries full burden. Discloses credit consumption ('Does not consume scan credits'), error conditions ('Returns error if no report exists'), and output structure ('ReportResult with score, certification status, and issues summary').

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Uses structured docstring format (Args/Returns/Example) that front-loads key information. First two sentences establish purpose and return value. All sentences add unique value beyond structured data, though 'Returns:' appears redundantly before the Args section.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Complete for a single-parameter tool with output schema. Description covers return values ('ReportResult'), error states, sibling differentiation, and resource constraints despite the formal output schema existing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0% (only 'title': 'Skill Url'), requiring description compensation. Provides semantic meaning ('The skill URL to get the report for') and includes example value ('https://github.com/jlowin/fastmcp') demonstrating expected format.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Clear specific verb 'Get' + resource 'public security report' + scope 'for a skill'. Explicitly distinguishes from sibling tool 'scan_skill' by stating it returns existing results 'without triggering a new scan'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states when to use: 'check if a skill has been previously scanned without triggering a new scan'. Also provides critical usage constraint 'Does not consume scan credits', clearly contrasting resource consumption with likely sibling behavior.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

scan_skillAInspect
Scan a GitHub repository or skill URL for security vulnerabilities.

This tool performs static analysis and AI-powered detection to identify:
- Hardcoded credentials and API keys
- Remote code execution patterns
- Data exfiltration attempts
- Privilege escalation risks
- OWASP LLM Top 10 vulnerabilities

Requires a valid X-API-Key header. Cached results (24h) do not consume credits.

Args:
    skill_url: GitHub repository URL (e.g., https://github.com/owner/repo)
               or raw file URL to scan

Returns:
    ScanResult with security score (0-100), recommendation, and detected issues.
    Score >= 80 is SAFE, 50-79 is CAUTION, < 50 is DANGEROUS.

Example:
    scan_skill("https://github.com/anthropics/anthropic-sdk-python")
ParametersJSON Schema
NameRequiredDescriptionDefault
skill_urlYes

Output Schema

ParametersJSON Schema
NameRequiredDescription
scoreYesSecurity score from 0-100 (higher is safer)
cachedYesWhether this result was from cache
issuesYesList of detected security issues
scan_idYesUnique identifier for this scan
skill_urlYesURL that was scanned
issues_countYesNumber of security issues found
recommendationYesSAFE, CAUTION, or DANGEROUS
scans_remainingNoRemaining scans this month (null if unlimited)
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description carries full burden. Excellently discloses: analysis methods (static + AI-powered), specific vulnerability categories (5 types including OWASP LLM Top 10), authentication requirements, caching behavior (24h TTL), and output interpretation (score thresholds for SAFE/CAUTION/DANGEROUS).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Well-structured with clear sections (purpose, vulnerability list, auth, caching, Args, Returns, Example). Front-loaded with main purpose. Slightly verbose due to vulnerability bullet list, but every element earns its place by providing necessary behavioral context.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite presence of output schema, description proactively explains return value semantics (ScanResult structure, 0-100 scoring rubric, risk thresholds). Combined with auth, caching, and parameter details, this provides complete context for a security scanning tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0% (parameter lacks description), but description fully compensates via the Args section: specifies 'GitHub repository URL' or 'raw file URL' and provides concrete example (https://github.com/owner/repo). This adds essential semantic meaning absent from the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Excellent clarity: 'Scan a GitHub repository or skill URL for security vulnerabilities' provides specific verb (Scan), resource (GitHub repository/skill URL), and goal. The detailed vulnerability list (hardcoded credentials, RCE patterns, etc.) further distinguishes this from sibling tools check_certification and get_report.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides clear prerequisites ('Requires a valid X-API-Key header') and caching guidance ('Cached results (24h) do not consume credits') which informs when to invoke. However, lacks explicit differentiation from siblings (e.g., when to use get_report instead).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Discussions

No comments yet. Be the first to start the discussion!

Try in Browser

Your Connectors

Sign in to create a connector for this server.