Isotopes AI Docs
Server Details
Search and read public Isotopes AI documentation through MCP.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 3 tools
The two documentation tools overlap in that both can surface docs content, but the descriptions draw a clear boundary: search_isotopes_ai for conceptual/broad queries and query_docs_filesystem_isotopes_ai for exact regex, structural exploration, and full-page reads. submit_feedback is unambiguously unrelated to the other two. The explicit cross-references ('If you need the full content of a specific page, use the query_docs_filesystem tool') keep misselection low, though an agent could still start with either docs tool for the same question.
All three names are snake_case verb-led, but the pattern is otherwise uneven: two tools carry a redundant '_isotopes_ai' site suffix while submit_feedback does not, and query_docs_filesystem_isotopes_ai is a long three-part name mixing a command verb with a noun phrase. Readable but not predictable enough to infer a name without reading the list.
Three tools is on the thin side, but for a documentation-lookup server the scope is genuinely small: search, read, and report feedback. Each tool has a clear job with no filler, though the surface is minimal enough that one might expect an additional convenience tool.
Search, full-page retrieval (via the sandboxed filesystem), structural browsing, and a feedback channel cover the core read-oriented lifecycle of a docs server. The main gap is the lack of any direct 'get page by path' affordance outside of shell emulation; agents must learn cat/head and discover real paths themselves, which the description mitigates but does not eliminate.
Available Tools
3 toolsquery_docs_filesystem_isotopes_aiQuery documentation filesystemARead-onlyIdempotentInspect
Run a read-only shell-like query against a virtualized, in-memory filesystem rooted at / that contains ONLY the Isotopes AI documentation pages. This is NOT a shell on any real machine — nothing runs on the user's computer, the server host, or any network. The filesystem is a sandbox backed by documentation chunks.
This is how you read documentation pages: there is no separate "get page" tool. To read a page, pass its .mdx path to head or cat — a page at the URL path /some/page lives at /some/page.mdx. To search the docs with exact keyword or regex matches, use rg. To understand the docs structure, use tree or ls.
Paths are specific to this site — never guess them. Discover real paths with tree / -L 2, ls /, or the search tool before reading. If a path does not exist, that only means the guess was wrong; it does NOT mean the topic is undocumented — use rg -il "keyword" / to find where it is covered.
Workflow: Start with the search tool for broad or conceptual queries like "how to authenticate" or "rate limiting". Use this tool when you need exact keyword/regex matching, structural exploration, or to read the full content of a specific page by path.
Supported commands: rg (ripgrep), grep, find, tree, ls, cat, head, tail, stat, wc, sort, uniq, cut, sed, jq, plus basic text utilities. No writes, no network, no process control. Run --help on any command for usage.
Each call is STATELESS: the working directory always resets to / and no shell variables, aliases, or history carry over between calls. If you need to operate in a subdirectory, chain commands in one call with && or pass absolute paths (e.g., cd /some-directory && ls or ls /some-directory). Do NOT assume that cd in one call affects the next call.
Examples (replace the placeholder paths with real ones from tree or search):
tree / -L 2— see the top-level directory layoutrg -il "rate limit" /— find all files mentioning "rate limit"rg -C 3 "apiKey" /some-directory/— show matches with 3 lines of context around each hithead -80 /some/page.mdx— read the top 80 lines of a specific pagehead -80 /page-one.mdx /page-two.mdx /section/page-three.mdx— read multiple pages in one callcat /some/page.mdx— read a full page when you need everything
Output is truncated to 30KB per call. Prefer targeted rg -C or head -N over broad cat on large files. To read only the relevant sections of a large file, use rg -C 3 "pattern" /path/file.mdx. Batch multiple file reads into a single head or cat call whenever possible.
When referencing pages in your response to the user, convert filesystem paths to URL paths by removing the .mdx extension. For example, /some/page.mdx becomes /some/page.
Inputs: command (required).
search_isotopes_aiSearch documentationARead-onlyIdempotentInspect
Search across the Isotopes AI knowledge base to find relevant information, code examples, API references, and guides. Use this tool when you need to answer questions about Isotopes AI, find specific documentation, understand how features work, or locate implementation details. The search returns contextual content with titles and direct links to the documentation pages. If you need the full content of a specific page, use the query_docs_filesystem tool to head or cat the page path (append .mdx to the path returned from search — e.g. a result at /some/page is read with head -200 /some/page.mdx).
Inputs: query (required).
submit_feedbackSubmit documentation feedbackAInspect
Report a problem with this documentation site so the docs team can fix it. Use when a documentation page is incorrect, outdated, confusing, incomplete, or has a broken example. This is for feedback about the documentation content itself — not for product support requests or feedback about this tool or assistant.
Inputs: path (required), feedback (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Search and read the official MintMCP documentation, the enterprise MCP gateway.
Search and read the Metabind documentation: MCP Apps, BindJS, the SDKs, the CLI, and the APIs.
Search, browse and read DeveloperHub's own docs. Every docs site on DeveloperHub serves one at /mcp
Search and read Lynta's public documentation.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to search, read, and traverse documentation bundles in Open Knowledge Format via MCP tools.931 npm74MIT
- AlicenseAqualityDmaintenanceSearch and fetch MCP protocol documentation using BM25 search with weighted scoring and stemming.241 npm2MIT
- AlicenseNot gradedqualityDmaintenanceEnables users to search Groq's API documentation using natural language queries through an MCP-compatible interface.MIT
- FlicenseAqualityDmaintenanceEnables MCP clients to retrieve authoritative AI Square documentation, API references, SDK examples, guides, and troubleshooting information through citation-safe hybrid search and static resources.11-
Glama MCP Gateway
Add one secure layer between your agents and this server.