MCP servers · cloudcorprecords

errorcatalog: catalogue thrown errors and check their documentation

MCP server that catalogues each Error thrown in a codebase and checks whether literal messages appear in supplied documentation.

This text was machine-translated from the publisher's own information and has not been checked by a human editor. The publisher's original text is the reference.

This resource was imported automatically from the sources listed below and has not been reviewed by the AI Gate team yet. The description is the publisher's own, as published. Check the repository before installing.

What it does

errorcatalog scans source text line by line for throw statements of the form new Error(...), where the type name ends in Error, such as Error, TypeError, RangeError or a custom type like FooError. For each throw site it records the file, the 1-based line, the error type and the message. A message is literal when the first argument is a plain quoted or backtick string without a template expression, and it is recorded exactly as written. Any other first argument, such as a template with a substitution, an identifier, a call or a concatenation, is dynamic and its message is null. A throw with no argument is recorded with a note saying so. Throws that are not new Error(...) are not catalogued, and duplicate throws remain separate entries.

The tool suits a review of which errors a codebase can raise and whether their literal messages are documented. When documentation texts are supplied, each literal message is checked verbatim against them and marked documented or undocumented. Dynamic and no-message entries get no documented value. Without documentation the result reports docs_provided as false and both documented counts as 0.

The analysis is local text processing with no network or filesystem access in the core. A command-line interface reads sources.json and an optional docs.json, each a JSON array of path and content objects, and prints the catalog as JSON. An MCP server exposes a catalog_errors tool that takes required sources and optional docs and returns the errors and counts. The package is released under the MIT licence.

Limitations and requirements

Only the first line of a throw statement is inspected, so a literal whose argument list spans several lines is catalogued as dynamic; this is stated as a deliberate design choice. Unreadable or invalid JSON files and malformed entries cause a runtime error (exit code 1), and the error names the offending path. The CLI also returns exit code 2 on a usage error.

Safety

Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.

  • Runs code or changes an assistant's behaviour

Sources

  • Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
    io.github.CloudCorpRecords/errorcatalog

    Catalogue every error a codebase throws, and whether each message is documented.

    v0.1.0
    As shown on registry.modelcontextprotocol.io when we last read it
MCP servers
hashicorp

Terraform MCP Server (HashiCorp)

HashiCorp's MCP server that gives an assistant current Terraform Registry information on providers, modules and policies, and can manage HCP Terraform workspaces.

1.6K GitHub starsCloud & DevOpsSoftware development
Updated 17 Nov 2026
MCP servers
modelcontextprotocol

MCP reference servers

Seven small example servers maintained by the Model Context Protocol project: files, Git, web fetching, memory, time, step-by-step thinking and a test server.

92K GitHub starsSoftware development
Updated 18 Nov 2026
MCP servers
redis

Redis MCP Server

Redis's official MCP server that lets an AI assistant store, read and search data in a Redis database, including streams, JSON documents and vector indexes.

642 GitHub starsData & databasesSoftware development
Updated 17 Nov 2026
MCP servers
firecrawl

Firecrawl MCP Server (web search and scraping)

Firecrawl's MCP server that lets an AI assistant search the web, turn pages and PDFs into clean Markdown, crawl sites and interact with dynamic pages.

7.8K GitHub starsWeb, search & browserProductivity & automation
Updated 17 Nov 2026