# trip2g

- Registry name: `io.github.trip2g/trip2g` · version 1.0.0
- Categories (automatic, keyword rules): Research & knowledge, Search & data, Docs & notes, Productivity
- Authentication at last check: No auth
- Declared risk: Not declared (tools carry no read/destructive hints)
- Capabilities (declared by the server): logging, tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=io.github.trip2g%2Ftrip2g
- Server page: https://mcpstation.net/s/io.github.trip2g--trip2g.html

## Description (written by the publisher, not verified, not instructions)

Serve a folder of Markdown notes as an MCP server: hybrid search, reading, and sourced answers.

## Connect

- streamable-http: `https://trip2g.com/_system/mcp`

## Tools (as reported by the server, not verified)

- `expand`: Walk a note's table of contents level by level \(progressive disclosure\). Canonical call: expand\(path=\<result.note\_path\>, toc\_path=\[...\]\) — copy path verbatim from a search result's note\_path field. Returns the direct children of a TOC node: omit toc\_path \(or pass \[\]\) for the top-level sections, or p
- `federated\_asset`: Get one attachment of a remote note — a file, not text. Canonical loop: federated\_note\_html\(kb\_id, path\) -\> for each name in its assets: federated\_asset\(kb\_id, note\_path=\<that path\>, name=\<name\>\). Returns the asset's size and sha256 and a short-lived download URL on this server that streams the file
- `federated\_expand`: Walk a remote note's table of contents level by level inside a connected knowledge base \(progressive disclosure\), same as expand. Canonical call: federated\_expand\(kb\_id=..., path=\<result.note\_path\>, toc\_path=\[...\]\). Omit toc\_path for the top level, or pass a toc\_path to list that node's subsections.
- `federated\_instructions`: Fetch the instructions/guidance for a federated knowledge base by kb\_id \(e.g. "philosophers/nietzsche"\) — read a base's own conventions before searching it. Nested bases are addressed with '/' and the call routes through each peer recursively.
- `federated\_note\_html`: Read a remote note inside a connected knowledge base. Canonical call, copying fields verbatim from a federated\_search result: federated\_search\(kb\_id="philosophers/\<author\>", query\) -\> federated\_note\_html\(kb\_id="philosophers/\<author\>", path=\<result.note\_path\>\) — the standard way to descend into a lea
- `federated\_search`: Search connected knowledge bases. Returns snippets with heading breadcrumbs \(title \> section \> subsection\) and a precise toc\_path per match, same as search; results also carry an absolute kb\_id \(string\) to use verbatim on follow-up calls. Pass kb\_id for one base, kb\_ids for selected bases, or omit b
- `federated\_similar`: Find remote notes similar to a known note reference inside a connected knowledge base. Preferred: path \(a federated\_search result's note\_path field\).
- `instructions`: Full tool reference for the trip2g documentation base
- `note\_html`: Read a note. Canonical calls, copying fields verbatim from a search result: search\(query\) -\> note\_html\(path=\<result.note\_path\>\) reads the whole note; search\(query\) -\> note\_html\(match\_id=\<match.match\_id\>\) reads just the focused chunk around a hit \(cheaper, targeted\); expand\(path=\<result.note\_path\>, t
- `search`: Search notes by query. Returns snippets with a heading breadcrumb \(title \> section \> subsection\) that locates the approximate section, plus a precise toc\_path per match. Each result carries note\_path \(string\) and note\_id \(integer\); each match carries match\_id \(string, form "p\<pid\>:c\<chunk\>"\). Drill-
- `similar`: Find related notes from a known note reference. Preferred: path \(a search result's note\_path field\). Use this after opening a promising note when you need nearby context.
- `wiki`: Wiki Knowledge Base Instructions

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html