Evidence on MCP servers before you install: publisher, source, provenance, advisories, changes.
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.
Evidence summary for an MCP server before you install or connect it: publisher identity level, provenance, known vulnerabilities, install scripts, maintenance, open warnings, checks that could not run, and recent changes. No warnings is NOT a safety guarantee.
MCP server name (e.g. io.github.github/github-mcp-server), catalog id, or GitHub repository URL
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
claude mcp add --transport http und-assay https://undassay.com/mcp
Evidence summary for an MCP server before you install or connect it: publisher identity level, provenance, known vulnerabilities, install scripts, maintenance, open warnings, checks that could not run, and recent changes. No warnings is NOT a safety guarantee.
| Argument | Type | Description |
|---|---|---|
| identifier* | string | MCP server name (e.g. io.github.github/github-mcp-server), catalog id, or GitHub repository URL |
{
"type": "object",
"required": [
"identifier"
],
"properties": {
"identifier": {
"type": "string",
"description": "MCP server name (e.g. io.github.github/github-mcp-server), catalog id, or GitHub repository URL"
}
},
"additionalProperties": false
}Metadata changes between consecutive published versions: new network hosts, replaced or added artifact sources, newly requested credentials.
| Argument | Type | Description |
|---|---|---|
| tool_id* | string |
{
"type": "object",
"required": [
"tool_id"
],
"properties": {
"tool_id": {
"type": "string"
}
},
"additionalProperties": false
}A single assertion of a tool (by field name) with the evidence records behind it: URL, fetch time, SHA-256.
| Argument | Type | Description |
|---|---|---|
| field* | string | |
| tool_id* | string |
{
"type": "object",
"required": [
"tool_id",
"field"
],
"properties": {
"field": {
"type": "string"
},
"tool_id": {
"type": "string"
}
},
"additionalProperties": false
}How a publisher is identified across ecosystems (MCP namespace, domain, GitHub, packages) and the state of each link.
| Argument | Type | Description |
|---|---|---|
| publisher_key* | string |
{
"type": "object",
"required": [
"publisher_key"
],
"properties": {
"publisher_key": {
"type": "string"
}
},
"additionalProperties": false
}One stable answer (schema_version 1) for connecting an MCP server: its validated remote URL and transport, packages, copy-paste setup for Claude Code and JSON configs, warnings by severity, checks that could not run, and contradicted claims. auth is null until Assay has checked the sign-in metadata of the server. Never a safety rating.
| Argument | Type | Description |
|---|---|---|
| identifier* | string | MCP server name, catalog id, or GitHub repository URL |
{
"type": "object",
"required": [
"identifier"
],
"properties": {
"identifier": {
"type": "string",
"description": "MCP server name, catalog id, or GitHub repository URL"
}
},
"additionalProperties": false
}Every assertion for a tool with its state (VERIFIED, CLAIMED, CONTRADICTED, STALE, UNKNOWN), reason, check and evidence records.
| Argument | Type | Description |
|---|---|---|
| tool_id* | string |
{
"type": "object",
"required": [
"tool_id"
],
"properties": {
"tool_id": {
"type": "string"
}
},
"additionalProperties": false
}Resolve an MCP server name, catalog id or GitHub repository URL to the real registry entry. If there is no exact match, returns the closest real names so look-alikes and invented names can be caught. No account needed.
| Argument | Type | Description |
|---|---|---|
| identifier* | string |
{
"type": "object",
"required": [
"identifier"
],
"properties": {
"identifier": {
"type": "string"
}
},
"additionalProperties": false
}Search cataloged MCP servers by keywords. Returns classification (verified_publisher = the publisher proved control of a domain or verified GitHub org, NOT that a company named in the tool made it / community / not_analyzed), identity level and warning counts.
| Argument | Type | Description |
|---|---|---|
| limit | integer | |
| query* | string | |
| official_only | boolean |
{
"type": "object",
"required": [
"query"
],
"properties": {
"limit": {
"type": "integer",
"maximum": 50,
"minimum": 1
},
"query": {
"type": "string"
},
"official_only": {
"type": "boolean"
}
},
"additionalProperties": false
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Oct 31, 2026.