Search, inspect, recommend, and explain rated AI tools through Agent Radar.
Call this server's tools from your browser. Nothing to install.
LLM provider API key used only by recommend_tools.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Return rating dimensions, explanations, penalties, and boosts for one tool_id.
Stable Agent Radar tool identifier, usually obtained from search_tools results.
Return rating dimensions, explanations, penalties, and boosts for one tool_id.
| Argument | Type | Description |
|---|---|---|
| tool_id* | string | Stable Agent Radar tool identifier, usually obtained from search_tools results. |
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"tool_id"
],
"properties": {
"tool_id": {
"type": "string",
"minLength": 1,
"description": "Stable Agent Radar tool identifier, usually obtained from search_tools results."
}
},
"additionalProperties": false
}Return one Tool Card and its Rating Result by stable tool_id.
| Argument | Type | Description |
|---|---|---|
| tool_id* | string | Stable Agent Radar tool identifier, usually obtained from search_tools results. |
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"tool_id"
],
"properties": {
"tool_id": {
"type": "string",
"minLength": 1,
"description": "Stable Agent Radar tool identifier, usually obtained from search_tools results."
}
},
"additionalProperties": false
}Recommend known tools for a task using request-scoped LLM credentials when required.
| Argument | Type | Description |
|---|---|---|
| task* | string | Natural-language development task for which Agent Radar should recommend suitable AI tools. |
| model | string | LLM provider model identifier recognized by Agent Radar. Omit it to use the server-configured or registry default model. |
| top_k | integer | Maximum number of recommended candidates to return, from 1 to 50. Defaults to 5 when omitted. |
| budget | string | Natural-language cost constraint, such as free, free_or_low_cost, or a project-specific budget. |
| environment | array | Execution contexts such as local development, CI, browser, cloud, IDE, or production. |
| output_format | string | Preferred presentation format for recommendation content: json or markdown. MCP still returns structured content. |
| existing_tools | array | Tools already available to the project or agent, used as compatibility and duplication context. |
| risk_tolerance |
Search Agent Radar Tool Cards by query text and optional type, tag, or risk filters.
| Argument | Type | Description |
|---|---|---|
| query | string | Free-text tool name, capability, or task to search for. Use an empty string to browse the highest-rated matching catalog entries. |
| top_k | integer | Maximum number of results to return, from 1 to 50. Defaults to 5. |
| filters | object | Optional exact-match filters applied before search ranking. |
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"query": {
"type": "string",
"default": "",
"description": "Free-text tool name, capability, or task to search for. Use an empty string to browse the highest-rated matching catalog entries."
},
"top_k": {
"type": "integer",
"default": 5,
"maximum": 50,
"minimum": 1,
"description": "Maximum number of results to return, from 1 to 50. Defaults to 5."
},
"filters": {
"type": "object",
"properties": {
"tags": {
"type": "array",
"items": {
"type": "string"
},
"description": "Exact catalog tags that every returned tool must contain."
},
"type": {
"enum": [
"mcp",
"skill",
"agent",
"framework",
"cli",
"prompt",
"rules",
"dataset",
"service"
],
"type": "string",
"description": "Exact Agent Radar tool type to include, such as mcp, skill, agent, framework, or cli."
},
"risk_level": {
"enum": [
"low",
"medium",
"high",
"critical",
"unknown"
],
"type": "string",
"description": "Exact assessed risk level to include: low, medium, high, critical, or unknown."
}
},
"description": "Optional exact-match filters applied before search ranking.",
"additionalProperties": false
}
},
"additionalProperties": false
}| string |
| Maximum preferred risk tolerance for the recommendation: low, medium, or high. |
| language_or_stack | array | Programming languages, frameworks, runtimes, or other stack constraints relevant to the task. |
| allowed_permissions | array | Permission scope names the caller is willing to allow; candidates outside these boundaries are treated conservatively. |
| preferred_tool_types | array | Agent Radar tool types to prefer when selecting candidates. |
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"task"
],
"properties": {
"task": {
"type": "string",
"minLength": 1,
"description": "Natural-language development task for which Agent Radar should recommend suitable AI tools."
},
"model": {
"type": "string",
"minLength": 1,
"description": "LLM provider model identifier recognized by Agent Radar. Omit it to use the server-configured or registry default model."
},
"top_k": {
"type": "integer",
"maximum": 50,
"minimum": 1,
"description": "Maximum number of recommended candidates to return, from 1 to 50. Defaults to 5 when omitted."
},
"budget": {
"type": "string",
"description": "Natural-language cost constraint, such as free, free_or_low_cost, or a project-specific budget."
},
"environment": {
"type": "array",
"items": {
"type": "string"
},
"description": "Execution contexts such as local development, CI, browser, cloud, IDE, or production."
},
"output_format": {
"enum": [
"json",
"markdown"
],
"type": "string",
"description": "Preferred presentation format for recommendation content: json or markdown. MCP still returns structured content."
},
"existing_tools": {
"type": "array",
"items": {
"type": "string"
},
"description": "Tools already available to the project or agent, used as compatibility and duplication context."
},
"risk_tolerance": {
"enum": [
"low",
"medium",
"high"
],
"type": "string",
"description": "Maximum preferred risk tolerance for the recommendation: low, medium, or high."
},
"language_or_stack": {
"type": "array",
"items": {
"type": "string"
},
"description": "Programming languages, frameworks, runtimes, or other stack constraints relevant to the task."
},
"allowed_permissions": {
"type": "array",
"items": {
"type": "string"
},
"description": "Permission scope names the caller is willing to allow; candidates outside these boundaries are treated conservatively."
},
"preferred_tool_types": {
"type": "array",
"items": {
"enum": [
"mcp",
"skill",
"agent",
"framework",
"cli",
"prompt",
"rules",
"dataset",
"service"
],
"type": "string"
},
"description": "Agent Radar tool types to prefer when selecting candidates."
}
},
"additionalProperties": false
}