Turn any REST API into an MCP server in minutes - no code, no deployments. MCPFire is a Meta-MCP server that manages all your tools.
MCPFire exposes a single tool 'ExecutableHttpRequestTool' with critical structural deficiencies. The tool is defined in mcpfire/mcp_builder.py but the input schema visible in the provided source is empty: {"type":"object","properties":{},"required":[],"additionalProperties":true}. This is a HARD FAIL under the rubric: 'If a tool has NO input schema at all: its schema score MUST be 0.' The tool description is extremely generic ('Executes HTTP requests and returns structured responses. Accepts variable substitution through arguments that replace placeholders in the request.') and provides no guidance on parameter semantics, expected formats, or how variable substitution works. No parameter-level descriptions are visible. The empty schema combined with 'additionalProperties: true' means the tool accepts any arbitrary JSON and LLMs cannot determine what fields are valid, required, or expected. This violates the core principle that every parameter needs a description and type definition. The tool is also described in past tense review notes as performing HTTP requests with 'variable substitution through arguments', but the schema does not show what 'arguments' means, what placeholders look like, or how substitution is invoked. The architecture suggests this is a meta-MCP server that dynamically creates tool definitions from configuration files (note references to 'config.yml' and HTTPRequest models), but those definitions are not visible in the provided source code. Without seeing the actual schema generation logic or example configurations, we cannot verify that downstream tools have proper schemas. This tool scores well below that due to the empty schema.
Executes HTTP requests and returns structured responses. Accepts variable substitution through arguments that replace placeholders in the request.
Tool input schema is empty (no properties defined). Schema shows only 'additionalProperties: true' with no typed parameters.
Tool description is generic and under-specified. Does not explain what 'variable substitution through arguments' means, what placeholder syntax is expected, or what fields the tool accepts. Violates pattern requirement that every tool description must answer: What does it do? When should I call it? What does it return?
No parameter-level descriptions visible. Tool accepts 'additionalProperties' but provides zero guidance on valid field names, types, or semantics. LLMs cannot infer parameter meaning from names alone (pattern:tool-description).
Inferred effective spec: 2025-06-18+.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-22 | F | 25 | 2025-06-18+ | v2 |
| 2026-03-09 | F | 0 | - | v1 |
Tool name does not follow verb_noun pattern. 'ExecutableHttpRequestTool' is a class name, not an action-oriented tool name. Pattern requires names like 'send_http_request' or 'execute_http_call'. Current name fails to convey intent to LLM.
No documented output schema. Tool description says 'returns structured responses' but does not specify what fields, types, or structure the response has. LLM cannot plan downstream operations or extract required data.
Dynamic tool definition strategy: MCPFire appears to generate tool definitions from config.yml at runtime (see config.py mcp_servers field and http_models references). The tool definitions are not visible in static source code analysis.