Read-only browser for The Log File store catalog: Chad Kovac's books and house skills, live.
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.
Read one book's full catalog entry, including its blurb, by slug.
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http catalog-browser https://thelogfile.com/mcp
Read one book's full catalog entry, including its blurb, by slug.
| Argument |
|---|
| Type |
|---|
| Description |
|---|
| slug* | string |
{
"type": "object",
"required": [
"slug"
],
"properties": {
"slug": {
"type": "string"
}
},
"additionalProperties": false
}List Chad Kovac's book catalog: titles, series, genres, formats, and Kindle price, each with its book door address.
No arguments.
{
"type": "object",
"properties": {},
"additionalProperties": false
}List the skills for sale at The Log File store, with tier, category, and price. Optionally filter by tier (Basic, Standard, Advanced).
| Argument | Type | Description |
|---|---|---|
| tier | string |
{
"type": "object",
"properties": {
"tier": {
"type": "string"
}
},
"additionalProperties": false
}Search skills and books by name, slug, or category.
| Argument | Type | Description |
|---|---|---|
| query* | string |
{
"type": "object",
"required": [
"query"
],
"properties": {
"query": {
"type": "string"
}
},
"additionalProperties": false
}The store facts a visiting bot needs: how many books stand published, the direct price, the skill points rule, free first chapters, and the store addresses.
No arguments.
{
"type": "object",
"properties": {},
"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 Nov 13, 2026.
No readOnlyHint / destructiveHint annotations, so clients can't tell a read from a write without asking.
Fix: Add annotations to each tool, e.g. { readOnlyHint: true } for tools that only read.