verify_mcp_serverPre-connect trust verdict for an MCP server, package, GitHub repo, or agent name before connecting an AI agent to it.
| Name | Required | Description | Default |
|---|---|---|---|
| server | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| slug | No | ||
| grade | Yes | ||
| server | Yes | ||
| reasons | Yes | ||
| tracked | Yes | ||
| trusted | Yes | ||
| resolved | Yes | ||
| confidence | Yes | ||
| submit_url | No | ||
| trust_score | Yes | ||
| tool_permissions | Yes | ||
| mcp_server_support | Yes |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Output schema / (root)Previous value: -nullNew value: +{
+ "properties": {
+ "confidence": {
+ "anyOf": [
+ {
+ "type": "number"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "title": "Confidence"
+ },
+ "grade": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "title": "Grade"
+ },
+ "mcp_server_support": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "title": "Mcp Server Support"
+ },
+ "reasons": {
+ "items": {
+ "type": "string"
+ },
+ "title": "Reasons",
+ "type": "array"
+ },
+ "resolved": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "title": "Resolved"
+ },
+ "server": {
+ "title": "Server",
+ "type": "string"
+ },
+ "slug": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "title": "Slug"
+ },
+ "submit_url": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "title": "Submit Url"
+ },
+ "tool_permissions": {
+ "items": {
+ "type": "string"
+ },
+ "title": "Tool Permissions",
+ "type": "array"
+ },
+ "tracked": {
+ "title": "Tracked",
+ "type": "boolean"
+ },
+ "trust_score": {
+ "anyOf": [
+ {
+ "type": "number"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "title": "Trust Score"
+ },
+ "trusted": {
+ "title": "Trusted",
+ "type": "boolean"
+ }
+ },
+ "required": [
+ "server",
+ "resolved",
+ "tracked",
+ "trusted",
+ "grade",
+ "trust_score",
+ "confidence",
+ "reasons",
+ "mcp_server_support",
+ "tool_permissions"
+ ],
+ "title": "VerifyMcpServerResult",
+ "type": "object"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, destructiveHint, idempotentHint, and openWorldHint, so safety profile is clear. The description adds that it returns a 'trust verdict', but does not detail what that verdict entails (e.g., score, boolean, reasons).
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, focused sentence with no redundancy or filler. Every word contributes to defining the tool's purpose and usage context.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description is adequate for a simple tool with one parameter and output schema. However, it does not explain the format of the trust verdict (e.g., boolean, string) or how to interpret results, leaving some ambiguity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0%, with no parameter description. The description clarifies that the 'server' parameter can include server names, packages, GitHub repos, or agent names, adding meaning beyond the schema. However, it does not specify format or examples.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool provides a 'pre-connect trust verdict' for various entities like MCP server, package, GitHub repo, or agent name. This is specific and informative, though it doesn't fully distinguish from the sibling 'check_agent_trust'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description indicates usage 'before connecting an AI agent', providing a clear when-to-use context. However, it does not explicitly state when not to use this tool compared to siblings like 'check_agent_trust' or 'get_agent_history'.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool has a distinct purpose: agent trust profile, comparison, history, leaderboard, categories, bulk scan, search, and MCP server verification. No overlap in functionality.
All tools use consistent snake_case and verb_noun pattern (e.g., check_agent_trust, verify_mcp_server). No mixing of conventions.
8 tools is well-scoped for a trust-tracking server, covering individual checks, comparisons, history, bulk scanning, and discovery without excess.
The tool surface covers all primary use cases: single agent lookups, comparisons, historical trends, leaderboards, category browsing, bulk scanning, and specific MCP server checks. No obvious gaps.