Zero-install security baseline for AI coding agents — OWASP/CWE-cited rules over MCP.
Scored across 2 tools
The two tools are clearly distinct: one retrieves the entire security baseline, while the other checks a specific action against that baseline. There is no overlap in their purposes, so an agent can easily choose between them.
Both tool names follow the same verb_noun pattern: 'check_action' and 'get_security_baseline'. This is consistent and predictable, making the tool surface easy to understand.
With only two tools, the server feels thin for a security-focused utility. However, the two tools cover the essential advisory operations (obtaining the baseline and checking actions), so the count is not unreasonable for a narrowly scoped purpose.
The server covers its stated purpose: providing the baseline and enabling action checks. Minor gaps exist (e.g., no tool to inspect specific rules or handle bulk checks), but the core advisory workflow is complete.
Advisory check: given a described action or command the agent is about to take, return the baseline security factlets that plausibly apply, so the agent can self-correct. Advisory only — does NOT block. Real-time blocking is Kernora Agent Security's paid Integrity Plane.
| Name | Required | Description | Default |
|---|---|---|---|
| action | Yes | the action/command about to run |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full responsibility for behavioral disclosure. It honestly states that the tool is advisory-only and does NOT block, and that blocking is a paid feature. It also implies non-exhaustive matching with 'plausibly apply.' While it doesn't explicitly say it's read-only, the advisory nature strongly implies no side effects.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, front-loaded with the primary purpose. Every clause earns its place: the behavior, the non-blocking caveat, and the paid alternative. There is no filler or redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple tool with one parameter and no output schema, the description fully captures what the agent needs to know: when to use it, what it does, and its limitations. The distinction from the paid blocking offering adds valuable context without requiring a full comparison to the sibling tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema has 100% coverage for the single 'action' parameter, with a clear description. The tool description adds only a slight rephrasing ('described action or command') and doesn't introduce new semantic details beyond what the schema already provides. Baseline 3 is appropriate when schema fully documents the parameter.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states a specific verb ('check') and resource ('action/command'), and explains the outcome: return baseline security factlets for self-correction. It distinguishes itself from the sibling tool by emphasizing the advisory, non-blocking nature, which is likely the intended contrast with get_security_baseline.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear usage context: use when the agent is about to take an action and wants advisory security feedback. It explicitly notes that it does NOT block, and mentions the paid Integrity Plane for real-time blocking, implying when the stronger alternative is needed. However, it does not explicitly compare with the sibling tool get_security_baseline or state exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Return Kernora Agent Security's curated security baseline — the known-good rules an AI coding agent should follow (secrets, injection, supply-chain, destructive ops, data protection). Advisory grounding.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must carry the full burden of behavioral disclosure. It makes clear this is an informational retrieval ('Return') and describes the nature of the content ('known-good rules'). However, it does not explicitly state side effects (e.g., read-only, no modifications) or whether the baseline is static, potentially leaving room for ambiguity.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise and front-loaded: the opening phrase immediately identifies the tool's purpose, followed by a compact list of content areas and a brief purpose statement. Every sentence adds value, and the total length is minimal.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the absence of an output schema, the description provides sufficient context by enumerating the domains covered. It also communicates the tool's advisory role. The only notable gap is that it does not mention how the baseline is returned (e.g., format), but for a simple reference tool, the coverage is adequate.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters, so there is no parameter semantics to explain. The description correctly uses simple, direct language appropriate for a parameterless tool, aligning with the baseline score of 4 for 0-parameter tools.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's function with a specific verb ('Return') and names the exact resource ('Kernora Agent Security's curated security baseline'). It elaborates on the contents (secrets, injection, supply-chain, destructive ops, data protection), distinguishing it from the sibling tool 'check_action' which presumably checks individual actions.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage through the phrase 'Advisory grounding,' suggesting the tool is meant to provide a reference for the agent's behavior. However, it does not explicitly state when to use this tool versus 'check_action', nor does it include exclusions or alternative scenarios.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
check_actionget_security_baselineAI-security knowledge as MCP: standards-mapped tools (OWASP, NIST, MITRE) for AI agents.
Zero-config MCP security scanner for AI-generated apps. 25K+ vulnerability patterns.
AgentGuard — 20-tool AI safety MCP: policy preflight, risk scoring, audit logging, rate limits.
Security firewall for AI agents — scans MCP calls for injection, secrets, and risks.
Add one secure layer between your agents and this server.