MCP registry: 138k servers crawled, handshake-validated, reliability-scored. 744 production-safe.
Inferred from the transports this listing declares (streamable-http). A client not listed here hasn’t been ruled out — it just isn’t something Forge can confirm.
Verification confirms publisher identity (repo ownership), not code safety. The security scan covers known CVEs and suspicious install scripts.
Read from a real MCP initialize → tools/list handshake against the declared endpoint. No tool was ever invoked — tools/list is the read-only introspection call the protocol defines for this. It reflects what the server advertised at that moment; a hosted endpoint is not pinned to any version and can change without notice.
https://arclan.ai/mcp4 tools · 280msquery_registrySearch 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 >…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 >…
| Parameter | Type | Description |
|---|---|---|
| capability | string | Filter by tool name or keyword (searches name, description, tools) |
| min_score | number | Minimum validation score 0–100 (default 0) |
| transport | string | Filter by transport type |
| 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 ind… |
| production_safe | boolean | Only return servers with uptime_7d > 97% and handshake_success_rate > 95%. Use when reliability matters. |
| read_only | boolean | Only return servers with no write or exec tools — safe for read-only agent workflows. |
| limit | number | Max results to return 1–20 (default 10) |
get_serverGet 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.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.
url: Links to undeclared domain: mcp.example.com| Parameter | Type | Description |
|---|---|---|
| url | string | The MCP server endpoint URL (e.g. "https://mcp.example.com/mcp") |
| id | string | Server name, registry ID slug, or any identifier (e.g. "github", "brave-search", "gateway-pipeworx-io-rpc-mcp") |
recommend_serverGet 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 lis…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 lis…
| Parameter | 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) |
| production_safe | boolean | Only return production-safe servers (uptime > 97%, handshake > 95%) |
| read_only | boolean | Only return servers with no write-classified tools |
| limit | number | Max results 1–20 (default: 5) |
report_serverSubmit 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).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).
| Parameter | Type | Description |
|---|---|---|
| serverUrl* | string | The MCP server endpoint URL that was used |
| outcome* | string | Result of using the server |
| agentId | string | Identifier for the reporting agent (optional) |
| toolsUsed | array | List of tool names that were called |
| turnsRequired | number | Number of turns to complete the task |
| latencyMs | number | Total wall-clock latency in milliseconds |
| taskCategory | string | Category of task attempted (e.g. "search", "write", "read") |
| taskDescription | string | Brief description of what the task was |
| errors | array | Array of error strings encountered during tool use |
| criterion | string | Specific reliability criterion being scored (enables structured component scoring) |
| componentScore | number | Score 0–100 for the specified criterion |
| severity | string | Severity of the worst issue encountered |
| environment | string | Environment the server was used in |
| evidenceRef | string | Trace ID, log URL, or other reference supporting this report |
4 of 4 tools published a description.
Tool names and descriptions are written by the publisher and shown verbatim as inert text. They are the strings an MCP client passes to a model, so Forge scans them for prompt-injection patterns — any finding appears with the security scan above. “Privileged” is a keyword match on the tool name, not an audit of what the tool does: a benign-sounding name can still do anything.
MCP registry: 138k servers crawled, handshake-validated, reliability-scored. 744 production-safe.
Linked names open Forge’s index of every entry observed exposing that tool. Browse all indexed tools.
This entry publishes no npm package, so Forge has no dependency tree for it. That is a gap in coverage — not a statement that it has no dependencies.