trip2g
Server Details
Serve a folder of Markdown notes as an MCP server: hybrid search, reading, and sourced answers.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- trip2g/trip2g
- GitHub Stars
- 41
- Server Listing
- trip2g
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 12 tools
The local/federated split is crisp: search/note_html/expand/similar/instructions each have a clear remote mirror (federated_*), and the descriptions spell out canonical call chains that make the search -> note_html -> expand workflow unambiguous. The only real overlap is between 'instructions' ('Full tool reference for the trip2g documentation base') and 'wiki' ('Wiki Knowledge Base Instructions'), plus 'federated_instructions', which an agent could plausibly confuse.
The federated_* family is perfectly consistent and predictable, mirroring local tools one-to-one. However, the base tools mix conventions: verbs (expand, search), noun_verb (note_html), and bare nouns (instructions, wiki, similar), so no single verb_noun pattern governs the set.
12 tools is well within a healthy range and each earns its place: six local operations plus their federated counterparts for remote bases, plus one extra for remote attachments. The duplication is purposeful (different scopes), not redundant.
The read/discovery lifecycle is well covered for both local and federated bases: search, read (full/chunk/section), structure walking, similarity, and instructions. The one visible gap is that attachments can be fetched remotely (federated_asset) but there is no local counterpart, and write operations are absent (acceptable for a read-only documentation base).
Available Tools
12 toolsexpandAInspect
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 pass a toc_path to list that section's subsections. Each child has title, level, path, and has_children. A section with subsections lists them; a section without subsections is returned in full (what note_html gives for that toc_path, plus section_html in the payload), so no second call is needed to read a leaf. This cannot be turned off, and a client that wants only structure never triggers it: has_children on each listed child says where descending would turn into reading.
Inputs: pid, href, last, path, +3 more.
federated_assetAInspect
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=, name=). Returns the asset's size and sha256 and a short-lived download URL on this server that streams the file from the remote base; fetch it with curl (the URL needs no other credential) and check the sha256. The file itself never comes back in the tool result. Only a directly connected base: kb_id without '/'.
Inputs: name (required), kb_id (required), note_path (required).
federated_expandAInspect
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. A section with subsections lists them; a section without subsections is returned in full, as federated_note_html would return it — has_children on each listed child says where that happens.
Inputs: kb_id (required), pid, href, last, +4 more.
federated_instructionsAInspect
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.
Inputs: kb_id (required).
federated_note_htmlAInspect
Read a remote note inside a connected knowledge base. Canonical call, copying fields verbatim from a federated_search result: federated_search(kb_id="philosophers/", query) -> federated_note_html(kb_id="philosophers/", path=<result.note_path>) — the standard way to descend into a leaf corpus and read real content there, not hub cards. federated_note_html(kb_id=..., match_id=<match.match_id>) reads just the focused chunk around a hit. Only pass pid/note_id if you already copied that exact id from a result. path is a string like "concepts/x.md"; match_id is "p:c"; a value like ":" or "/hub/goethe.md" is a PATH, not a note_id.
Inputs: kb_id (required), pid, href, path, +3 more.
federated_searchAInspect
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 both to fan out. Nested bases are addressed with '/': kb_id "philosophers/nietzsche" routes through the 'philosophers' peer to the base it federates (recursive), up to 3 levels deep. Canonical call: federated_search(kb_id="philosophers/", query) -> federated_note_html(kb_id="philosophers/", path=<result.note_path>) — the standard way to descend into a leaf corpus and read real content, not hub cards. The optional fields each run an extra search whose results are merged with the main one; fill them to find more.
Inputs: query (required), kb_id, limit, kb_ids, +4 more.
federated_similarAInspect
Find remote notes similar to a known note reference inside a connected knowledge base. Preferred: path (a federated_search result's note_path field).
Inputs: kb_id (required), pid, href, path, +2 more.
instructionsCInspect
Full tool reference for the trip2g documentation base
note_htmlAInspect
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>, toc_path=[...]) -> note_html(path=<result.note_path>, toc_path=[...]) reads one exact section. Only pass pid/note_id if you already copied that exact integer from a result's note_id field — never invent one. path is a string like "concepts/x.md"; match_id is "p:c"; a value like ":" or "/hub/goethe.md" is a PATH, not a note_id.
Inputs: pid, href, path, note_id, +3 more.
searchAInspect
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:c"). Drill-down workflow: 1) search to find the approximate section via the breadcrumb; 2) call note_html(path=<result.note_path>, toc_path=[...]) to read the matched section, or expand(path=<result.note_path>, toc_path=[...]) to navigate the note's structure level by level; 3) note_html(path=<result.note_path>, match_id=<match.match_id>) for a focused chunk window. Each match also carries section_url — a link straight to that heading, for citing the section rather than the whole note. The optional fields each run an extra search whose results are merged with the main one; fill them to find more.
Inputs: query (required), limit, short_query, detail_limit, +2 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Markdown-based note-taking with a hosted MCP server. Your notes serve you and your AI.
Hosted MCP server for Obsidian Sync vaults: read, search, edit notes. Not affiliated with Obsidian.
Agent-native MCP server over the public saagarpatel.dev corpus. Read-only, stateless.
MCP server for querying Forkast documentation
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceTurns markdown note directories into an MCP knowledge assistant server, enabling hybrid search, explanations, quizzes, and comparisons for any MCP-compatible AI tool.MIT
- AlicenseNot gradedqualityBmaintenanceServes a folder as an MCP knowledge server: it indexes text, code, PDFs, office documents and audio or video, then answers search and ask calls with citations that name the file, the line range, the page or the time range. Runs fully local with Ollama by default; Mistral, OpenAI, Gemini and Anthropic are optional providers.4MIT
- AlicenseBqualityCmaintenanceEnables hybrid dense and BM25 search over a markdown vault, with tools for reading, writing, grepping, and managing notes through any MCP-compatible client.12MIT
- AlicenseAqualityBmaintenanceEnables MCP-capable clients to search a folder of Markdown notes with hybrid full-text and embedding retrieval, plus read, write, append, and reindex operations that keep a single shared SQLite index in sync with the files.92MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.