protogrid

Search MCP servers by intent

search

Read-onlyIdempotent

Hybrid (keyword + semantic) search over servers and their tools. Filter by connection class to keep only what you can reach autonomously (R0, R1).

Input Schema

TableJSON Schema

Name	Required	Description
`q`	Yes	What you want to do, in plain words, e.g. 'send an email' or 'query postgres'
`class`	No	Connection classes to keep, e.g. ['R0','R1']
`flags`	No	Trust flags that must all be present
`limit`	No	Results to return (default 10)
`category`	No
`min_trust`	No	Minimum trust score 0-100
`transport`	No
`min_quality`	No	Minimum quality score 0-100; unscored servers are left out
`exclude_flags`	No	Trust flags, any of which excludes a server, e.g. ['multi-version-spam','duplicate-repo']
`quality_flags`	No	Quality flags that must all be present
`owner_verified`	No	true: only servers whose owner proved control of the namespace (not an audit)
`exclude_quality_flags`	No	Quality flags, any of which excludes a server, e.g. ['known-vulns']

Output Schema

TableJSON Schema

Name	Required	Description
`mode`	Yes
`count`	Yes
`query`	Yes
`results`	Yes
`next_actions`	Yes	Follow-up calls: action is the tool, arguments are ready to pass ({placeholders} are yours to fill)

Schema Changelog

Changes observed during successful MCP inspections.

Changed7 schema fields changedSep 29, 2026

addedInput schema / properties / exclude_quality_flags

Added value: +{
+  "description": "Quality flags, any of which excludes a server, e.g. ['known-vulns']",
+  "items": {
+    "enum": [
+      "known-vulns",
+      "outdated-mcp-sdk"
+    ],
+    "type": "string"
+  },
+  "type": "array"
+}

addedInput schema / properties / min_quality

Added value: +{
+  "description": "Minimum quality score 0-100; unscored servers are left out",
+  "maximum": 100,
+  "minimum": 0,
+  "type": "integer"
+}

addedInput schema / properties / owner_verified

Added value: +{
+  "description": "true: only servers whose owner proved control of the namespace (not an audit)",
+  "type": "boolean"
+}

addedInput schema / properties / quality_flags

Added value: +{
+  "description": "Quality flags that must all be present",
+  "items": {
+    "enum": [
+      "known-vulns",
+      "outdated-mcp-sdk"
+    ],
+    "type": "string"
+  },
+  "type": "array"
+}

addedOutput schema / properties / results / items / properties / owner_verified

Added value: +{
+  "description": "The owner proved control of the namespace; not an audit",
+  "type": "boolean"
+}

addedOutput schema / properties / results / items / properties / quality_flags

Added value: +{
+  "description": "known-vulns, outdated-mcp-sdk: raised by failing dependency checks",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

changedOutput schema / properties / results / items / required

Previous value: -[
-  "name",
-  "title",
-  "description",
-  "connection_class",
-  "autonomous",
-  "human_steps",
-  "categories",
-  "trust_score",
-  "trust_flags",
-  "quality_score",
-  "quality_label",
-  "tool_count",
-  "score",
-  "matched_tools"
-]New value: +[
+  "name",
+  "title",
+  "description",
+  "connection_class",
+  "autonomous",
+  "human_steps",
+  "categories",
+  "trust_score",
+  "trust_flags",
+  "quality_score",
+  "quality_label",
+  "quality_flags",
+  "owner_verified",
+  "tool_count",
+  "score",
+  "matched_tools"
+]

Changed1 schema field changedSep 28, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "additionalProperties": {},
+  "properties": {
+    "count": {
+      "maximum": 9007199254740991,
+      "minimum": -9007199254740991,
+      "type": "integer"
+    },
+    "mode": {
+      "enum": [
+        "hybrid",
+        "keyword"
+      ],
+      "type": "string"
+    },
+    "next_actions": {
+      "description": "Follow-up calls: action is the tool, arguments are ready to pass ({placeholders} are yours to fill)",
+      "items": {
+        "additionalProperties": {},
+        "properties": {
+          "action": {
+            "type": "string"
+          },
+          "arguments": {
+            "additionalProperties": {},
+            "propertyNames": {
+              "type": "string"
+            },
+            "type": "object"
+          }
+        },
+        "required": [
+          "action"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "query": {
+      "type": "string"
+    },
+    "results": {
+      "items": {
+        "additionalProperties": {},
+        "properties": {
+          "autonomous": {
+            "description": "True when an agent can connect with no human step",
+            "type": "boolean"
+          },
+          "categories": {
+            "items": {
+              "type": "string"
+            },
+            "type": "array"
+          },
+          "connection_class": {
+            "description": "R0 remote no auth, R1 static secret, R2 OAuth, L0 local package",
+            "enum": [
+              "R0",
+              "R1",
+              "R2",
+              "L0",
+              "unknown"
+            ],
+            "type": "string"
+          },
+          "description": {
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "human_steps": {
+            "items": {
+              "type": "string"
+            },
+            "type": "array"
+          },
+          "matched_tools": {
+            "items": {
+              "additionalProperties": {},
+              "properties": {
+                "description": {
+                  "type": [
+                    "string",
+                    "null"
+                  ]
+                },
+                "name": {
+                  "type": "string"
+                }
+              },
+              "required": [
+                "name",
+                "description"
+              ],
+              "type": "object"
+            },
+            "type": "array"
+          },
+          "name": {
+            "description": "Official reverse-DNS name, the argument of every other tool",
+            "type": "string"
+          },
+          "quality_label": {
+            "description": "strong, good, needs work, poor, new, not scored or blocked",
+            "type": "string"
+          },
+          "quality_score": {
+            "type": [
+              "number",
+              "null"
+            ]
+          },
+          "score": {
+            "description": "Relevance of this result to the query",
+            "type": "number"
+          },
+          "title": {
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "tool_count": {
+            "maximum": 9007199254740991,
+            "minimum": -9007199254740991,
+            "type": "integer"
+          },
+          "trust_flags": {
+            "items": {
+              "type": "string"
+            },
+            "type": "array"
+          },
+          "trust_score": {
+            "type": [
+              "number",
+              "null"
+            ]
+          }
+        },
+        "required": [
+          "name",
+          "title",
+          "description",
+          "connection_class",
+          "autonomous",
+          "human_steps",
+          "categories",
+          "trust_score",
+          "trust_flags",
+          "quality_score",
+          "quality_label",
+          "tool_count",
+          "score",
+          "matched_tools"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    }
+  },
+  "required": [
+    "query",
+    "mode",
+    "count",
+    "results",
+    "next_actions"
+  ],
+  "type": "object"
+}

Changed1 schema field changedSep 23, 2026

changedInput schema / $schema

Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"

First observedSep 23, 2026

TDQS

A3.6/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, non-destructive, closed-world, so the safety profile is covered. The description adds the hybrid keyword+semantic retrieval behavior and the reachability rationale for class filtering, which is modest extra context but does not cover pagination or result ordering.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with the core capability followed by the operational tip. No filler or repetition of structured fields.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, return values need no explanation, and the rich schema covers most parameters. The description is adequate for a 12-param search tool, though a word on result ordering or how hybrid ranking behaves would round it out.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 83%, so most of the 12 parameters are already self-documenting with examples and semantics. The description only echoes the `class` filter idea and adds nothing about the many trust/quality/flag parameters beyond what the schema states.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

'Hybrid (keyword + semantic) search over servers and their tools' gives a specific verb and resource clearly. It distinguishes itself from siblings like get_server and list_tools by being the discovery/search entry point, though it never names a sibling explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The second sentence hints at usage: filter by connection class 'to keep only what you can reach autonomously (R0, R1)'. That is a useful intent-level cue but there is no explicit when-to-use-this-vs-alternatives or when-not-to-use guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All protogrid tools Inspect

Try in Browser

Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?