Skip to main content
Glama
Jambozx

OnlineCyberTools MCP (280+ filterable tools)

security_csp_generator

Read-onlyIdempotent

Build, parse, or analyze Content-Security-Policy headers with severity-ranked warnings. Assemble directives or audit existing policies for misconfigurations.

Instructions

Content-Security-Policy Builder, Parser, and Analyzer. Build a Content-Security-Policy header value from a directives map, parse an existing CSP header string into structured directives, or analyze either form for misconfigurations ranked by severity (critical to info). Set operation to build, parse, or analyze. This assembles and audits the header TEXT only - it does not deploy, send, or apply the policy to any server. Use it to author or review a CSP; for full Apache or Nginx config files use linux_web_server_config_generator, for Apache rewrite and header rules use security_htaccess_generator, and for raw openssl CLI invocations use security_openssl_command_builder. Runs locally on the policy you provide: read-only, non-destructive, contacts no external service, and is rate-limited (30 requests/minute for anonymous callers). Returns the serialized header value, normalized directives, an HTML meta-tag form (build only), and severity-ranked warnings.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
operationYesMode: build serializes a directives map into a header (requires policy); parse splits a header string into directives (requires value); analyze audits either input for weaknesses (requires value or policy).
policyNoCSP directives map keyed by directive name (default-src, script-src, style-src, img-src, connect-src, frame-ancestors, base-uri, form-action, object-src, and so on). Each value is an array of source tokens (such as self, unsafe-inline, https: or a nonce/hash) or a single space-separated string. Boolean directives like upgrade-insecure-requests take an empty array or true. Required for build; accepted by analyze.
valueNoAn existing CSP header value to parse or analyze, for example default-src self then script-src self. Required for parse; accepted by analyze.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
successNoTrue when the operation completed without error.
operationNoThe operation performed (build, parse, or analyze).
resultNoOperation output. build returns header/value/directives/warnings/htmlMetaTag; parse returns value/directives/warnings; analyze returns warnings only.
Behavior5/5

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

The annotations (readOnlyHint=true, destructiveHint=false, idempotentHint=true) are reinforced with explicit behavioral context: 'Runs locally … read-only, non-destructive, contacts no external service, and is rate-limited'. It also describes return values (serialized header, normalized directives, HTML meta-tag, severity-ranked warnings), adding significant transparency.

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

Conciseness5/5

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

The description is concise yet comprehensive, starting with the core purpose, then detailing operations, clarifying what it doesn't do, providing sibling differentiation, and adding behavioral notes. Every sentence serves a purpose without being verbose.

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?

For a multi-operation tool with parameters, annotations, and an output schema, the description covers all critical aspects: all three operations with their input requirements, behavioral constraints (read-only, rate-limited), output details (header value, directives, HTML meta-tag, warnings), and links to related tools. There are no gaps.

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 100% with each parameter having a description. The description goes further by explaining operation modes and their parameter dependencies ('build serializes... requires policy; parse splits... requires value; analyze audits... requires value or policy'). It also elaborates on the policy structure (directives map, arrays of tokens, boolean directives), exceeding the schema's brief descriptions.

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?

The description clearly states 'Content-Security-Policy Builder, Parser, and Analyzer' and immediately explains the three modes (build, parse, analyze). It distinguishes from sibling tools by naming alternatives for full Apache/Nginx configs (linux_web_server_config_generator, security_htaccess_generator, security_openssl_command_builder), effectively differentiating the tool.

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?

The description explicitly tells when to use this tool ('Use it to author or review a CSP') and when to use alternatives ('for full Apache or Nginx config files use...'). It also states what the tool does not do ('it does not deploy, send, or apply the policy'), providing clear guardrails.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Jambozx/onlinecybertools-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server