MCP registry: 138k servers crawled, handshake-validated, reliability-scored. 744 production-safe.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
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.
Get full details for a specific MCP server. Pass the server name (e.g. "GitHub", "Brave Search"), registry ID slug, or endpoint URL. Returns score, state, tools list, latency, and recent test history.
Server name, registry ID slug, or any identifier (e.g. "github", "brave-search", "gateway-pipeworx-io-rpc-mcp")
The MCP server endpoint URL (e.g. "https://mcp.example.com/mcp")
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Get full details for a specific MCP server. Pass the server name (e.g. "GitHub", "Brave Search"), registry ID slug, or endpoint URL. Returns score, state, tools list, latency, and recent test history.
| Argument | Type | Description |
|---|---|---|
| id | string | Server name, registry ID slug, or any identifier (e.g. "github", "brave-search", "gateway-pipeworx-io-rpc-mcp") |
| url | string | The MCP server endpoint URL (e.g. "https://mcp.example.com/mcp") |
{
"type": "object",
"properties": {
"id": {
"type": "string",
"description": "Server name, registry ID slug, or any identifier (e.g. \"github\", \"brave-search\", \"gateway-pipeworx-io-rpc-mcp\")"
},
"url": {
"type": "string",
"description": "The MCP server endpoint URL (e.g. \"https://mcp.example.com/mcp\")"
}
}
}Search the Arclan registry for MCP servers. By default returns only connectable servers (active, mcp_partial, auth_gated). Use status=stdio to browse local-only servers available for installation. Use status=all to query the full index. Use production_safe=true to restrict to servers with uptime > 97% and handshake success > 95%. Use read_only=true to restrict to servers with no write or exec tools. Use this before connecting to an MCP server to check its validation status and score. After using a server, call report_server to contribute reliability data.
| Argument | Type | Description |
|---|---|---|
| limit | number | Max results to return 1–20 (default 10) |
| status | string | Filter by state. Default (omit): connectable states only (active + mcp_partial + auth_gated). Use "stdio" for local-install catalog. Use "all" for the full index. |
| min_score | number | Minimum validation score 0–100 (default 0) |
| read_only | boolean | Only return servers with no write or exec tools — safe for read-only agent workflows. |
| transport | string | Filter by transport type |
| capability | string | Filter by tool name or keyword (searches name, description, tools) |
| production_safe | boolean | Only return servers with uptime_7d > 97% and handshake_success_rate > 95%. Use when reliability matters. |
{
"type": "object",
"properties": {
"limit": {
"type": "number",
"description": "Max results to return 1–20 (default 10)"
},
"status": {
"enum": [
"active",
"mcp_partial",
"auth_gated",
"stdio",
"unreachable",
"invalid",
"zombie",
"all"
],
"type": "string",
"description": "Filter by state. Default (omit): connectable states only (active + mcp_partial + auth_gated). Use \"stdio\" for local-install catalog. Use \"all\" for the full index."
},
"min_score": {
"type": "number",
"description": "Minimum validation score 0–100 (default 0)"
},
"read_only": {
"type": "boolean",
"description": "Only return servers with no write or exec tools — safe for read-only agent workflows."
},
"transport": {
"enum": [
"http",
"sse",
"stdio",
"unknown"
],
"type": "string",
"description": "Filter by transport type"
},
"capability": {
"type": "string",
"description": "Filter by tool name or keyword (searches name, description, tools)"
},
"production_safe": {
"type": "boolean",
"description": "Only return servers with uptime_7d > 97% and handshake_success_rate > 95%. Use when reliability matters."
}
}
}Get ranked MCP server recommendations for a task. Returns servers scored by production safety, keyword relevance, registry score, latency, and freshness. Each result includes a reason code array explaining why it was ranked. Use this instead of query_registry when you want an opinionated ranked list rather than a filtered search.
| Argument | Type | Description |
|---|---|---|
| q | string | Task or capability query — e.g. "search the web" or "read files" |
| auth | boolean | Include servers that require authentication (default: true) |
| limit | number | Max results 1–20 (default: 5) |
| read_only | boolean | Only return servers with no write-classified tools |
| production_safe | boolean | Only return production-safe servers (uptime > 97%, handshake > 95%) |
{
"type": "object",
"properties": {
"q": {
"type": "string",
"description": "Task or capability query — e.g. \"search the web\" or \"read files\""
},
"auth": {
"type": "boolean",
"description": "Include servers that require authentication (default: true)"
},
"limit": {
"type": "number",
"description": "Max results 1–20 (default: 5)"
},
"read_only": {
"type": "boolean",
"description": "Only return servers with no write-classified tools"
},
"production_safe": {
"type": "boolean",
"description": "Only return production-safe servers (uptime > 97%, handshake > 95%)"
}
}
}Submit an agent usage report for an MCP server. Reports are aggregated and influence registry trust scores. Call this after using an MCP server so the registry can track real-world reliability. Supports both a simple outcome report and a structured scoring report (criterion + component_score).
| Argument | Type | Description |
|---|---|---|
| errors | array | Array of error strings encountered during tool use |
| agentId | string | Identifier for the reporting agent (optional) |
| outcome* | string | Result of using the server |
| severity | string | Severity of the worst issue encountered |
| criterion | string | Specific reliability criterion being scored (enables structured component scoring) |
| latencyMs | number | Total wall-clock latency in milliseconds |
| serverUrl* | string | The MCP server endpoint URL that was used |
| toolsUsed | array | List of tool names that were called |
| environment | string |
| Environment the server was used in |
| evidenceRef | string | Trace ID, log URL, or other reference supporting this report |
| taskCategory | string | Category of task attempted (e.g. "search", "write", "read") |
| turnsRequired | number | Number of turns to complete the task |
| componentScore | number | Score 0–100 for the specified criterion |
| taskDescription | string | Brief description of what the task was |
{
"type": "object",
"required": [
"serverUrl",
"outcome"
],
"properties": {
"errors": {
"type": "array",
"items": {
"type": "string"
},
"description": "Array of error strings encountered during tool use"
},
"agentId": {
"type": "string",
"description": "Identifier for the reporting agent (optional)"
},
"outcome": {
"enum": [
"success",
"failure",
"partial"
],
"type": "string",
"description": "Result of using the server"
},
"severity": {
"enum": [
"info",
"warning",
"error",
"critical"
],
"type": "string",
"description": "Severity of the worst issue encountered"
},
"criterion": {
"enum": [
"output_reliability",
"side_effect_transparency",
"failure_handling",
"rate_limits",
"agent_feedback"
],
"type": "string",
"description": "Specific reliability criterion being scored (enables structured component scoring)"
},
"latencyMs": {
"type": "number",
"description": "Total wall-clock latency in milliseconds"
},
"serverUrl": {
"type": "string",
"description": "The MCP server endpoint URL that was used"
},
"toolsUsed": {
"type": "array",
"items": {
"type": "string"
},
"description": "List of tool names that were called"
},
"environment": {
"enum": [
"prod",
"staging",
"dev",
"unknown"
],
"type": "string",
"description": "Environment the server was used in"
},
"evidenceRef": {
"type": "string",
"description": "Trace ID, log URL, or other reference supporting this report"
},
"taskCategory": {
"type": "string",
"description": "Category of task attempted (e.g. \"search\", \"write\", \"read\")"
},
"turnsRequired": {
"type": "number",
"description": "Number of turns to complete the task"
},
"componentScore": {
"type": "number",
"description": "Score 0–100 for the specified criterion"
},
"taskDescription": {
"type": "string",
"description": "Brief description of what the task was"
}
}
}