trip2g

Measured conclusion: Deep-tested. L2 outcome: tools_ok.

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

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "trip2g": {
      "url": "https://trip2g.com/_system/mcp",
      "transport": "streamable-http"
    }
  }
}

Measured tools (12)

• 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 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.

  Parameters:

  • pid — number — Non-negative integer (uint64) note id, copied verbatim from a search result's note_id field. Not a path, slug, or match_id. Prefer path
  • href — string — String note href, copied verbatim from a search result's href field
  • last — number — List only this many of the newest subsections instead of all of them. A note that gains a dated section a day has hundreds of them after a year, and reading the whole listing to reach the latest few is the cost this avoids. The summary, total_children and omitted say what was left out, so a bounded listing never reads as a complete one. Bounds that meet or overlap return everything rather than repeating a run.
  • path — string — String note path, e.g. "concepts/maska-i-glubina.md" — copy verbatim from a search result's note_path field. The default, preferred way to reference a note
  • first — number — List only this many of the oldest subsections. Pair it with last to get how a subject started and where it stands now, leaving out the middle; the summary marks the gap where it falls.
  • note_id — number — Same as pid: non-negative integer (uint64) note id, copied verbatim from a search result's note_id field. Not a path, slug, or match_id. Prefer path
  • toc_path — array — Breadcrumb path to the node to expand, e.g. ["Chapter 1"]. Omit or [] for the top level.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• 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 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 '/'.

  Parameters:

  • kb_id (required) — string — Directly connected knowledge base id, as in federated_note_html
  • note_path (required) — string — The remote note's path, exactly as passed to federated_note_html
  • name (required) — string — One name from that note's assets, copied verbatim, e.g. "files/attach.zip"

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• 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. 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.

  Parameters:

  • kb_id (required) — string — Target knowledge base id; nested bases use '/' (e.g. "philosophers/nietzsche" routes through the 'philosophers' peer, recursively). Federation nests up to 3 levels deep (kb_id path segments); a deeper path is rejected.
  • pid — number — Non-negative integer (uint64) remote note id, copied verbatim from a federated_search result's note_id field. Prefer path
  • href — string — String remote note href, copied verbatim from a federated_search result's href field
  • last — number — List only this many of the newest subsections instead of all of them, as expand does. The summary, total_children and omitted say what was left out.
  • path — string — String remote note path, copied verbatim from a federated_search result's note_path field
  • first — number — List only this many of the oldest subsections, as expand does.
  • note_id — string — Same remote note id as pid, but as a STRING (uint64) — stringify the federated_search result's note_id field. Prefer path
  • toc_path — array — Breadcrumb path to the node to expand. Omit or [] for the top level.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• 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.

  Parameters:

  • kb_id (required) — string — Target knowledge base id; nested bases use '/' (e.g. "philosophers/nietzsche" routes through the 'philosophers' peer, recursively)

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• 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 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<pid>:c<chunk>"; a value like ":" or "/hub/goethe.md" is a PATH, not a note_id.

  Parameters:

  • kb_id (required) — string — Target knowledge base id; nested bases use '/' (e.g. "philosophers/nietzsche" routes through the 'philosophers' peer, recursively). Federation nests up to 3 levels deep (kb_id path segments); a deeper path is rejected.
  • pid — number — Non-negative integer (uint64) remote note id, copied verbatim from a federated_search result's note_id field. Not a path, slug, or match_id. Prefer path or match_id
  • href — string — String remote note href or absolute URL, copied verbatim from a federated_search result's href field
  • path — string — String remote note path, copied verbatim from a federated_search result's note_path field
  • note_id — string — Same remote note id as pid, but as a STRING (uint64) — stringify the federated_search result's note_id field. Not a path, slug, or match_id. Prefer path or match_id
  • match_id — string — String chunk id of the form "p<pid>:c<chunk>", copied verbatim from a remote search match's match_id field; alone it is enough to resolve the note
  • toc_path — array — Breadcrumb path to a specific section, e.g. ["Chapter 1", "Introduction"]. Use toc_path from a federated_search match, or a child path from federated_expand. Wins over match_id when both are given. Without either the whole note comes back.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• 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 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/<author>", query) -> federated_note_html(kb_id="philosophers/<author>", 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.

  Parameters:

  • query (required) — string — The user's question exactly as they asked it. Do not rewrite it.
  • kb_id — string — Target knowledge base id; nested bases use '/' (e.g. "philosophers/nietzsche" routes through the 'philosophers' peer, recursively). Federation nests up to 3 levels deep (kb_id path segments); a deeper path is rejected.
  • limit — number — Max number of results to return (default 6)
  • kb_ids — array — Target knowledge base ids; each accepts the same nested 'peer/base' form as kb_id
  • short_query — string — Optional. 2-3 words in English that the answering note is sure to contain: the main term and one qualifier, in dictionary form (nominative singular, infinitive). A short phrase, not a list; no punctuation. Keyword search needs every word to match, so fewer precise words beat many.
  • detail_limit — number — How many results include full snippet matches; results beyond this are returned as lightweight previews (title, path, score) to save context (default 3)
  • expected_answer — string — Optional. One or two sentences in English that the answering note itself could contain, written the way the notes state facts (e.g. 'To reset a password, open Settings and select Security.'). Not a description of what the note covers, not a question. If unsure of details, stay general but keep it a statement of fact.
  • rephrased_query — string — Optional. The question asked another way in English: different words, and the canonical name of what it asks about if you know it. One sentence.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• 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).

  Parameters:

  • kb_id (required) — string — Target knowledge base id; nested bases use '/' (e.g. "philosophers/nietzsche" routes through the 'philosophers' peer, recursively). Federation nests up to 3 levels deep (kb_id path segments); a deeper path is rejected.
  • pid — number — Non-negative integer (uint64) remote note id, copied verbatim from a federated_search result's note_id field. Prefer path
  • href — string — String remote note href, copied verbatim from a federated_search result's href field
  • path — string — String remote note path, copied verbatim from a federated_search result's note_path field
  • limit — number — Max number of results
  • note_id — string — Same remote note id as pid, but as a STRING (uint64) — stringify the federated_search result's note_id field. Prefer path

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• instructions

  Full tool reference for the trip2g documentation base

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• 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>, 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<pid>:c<chunk>"; a value like ":" or "/hub/goethe.md" is a PATH, not a note_id.

  Parameters:

  • pid — number — Non-negative integer (uint64) note id, copied verbatim from a search result's note_id field. Not a path, slug, or match_id — a value like ":" or "/hub/goethe.md" is a path, not a note id. Prefer path or match_id
  • href — string — String note href or absolute URL, copied verbatim from a search result's href field
  • path — string — String note path, e.g. "concepts/maska-i-glubina.md" — copy verbatim from a search result's note_path field. The default, preferred way to open a note
  • note_id — number — Same as pid: non-negative integer (uint64) note id, copied verbatim from a search result's note_id field. Not a path, slug, or match_id. Prefer path or match_id
  • match_id — string — String chunk id of the form "p<pid>:c<chunk>" (e.g. "p32:c4"), copied verbatim from a search match's match_id field. Alone it is enough to resolve the note and reads a focused window around that hit
  • toc_path — array — Breadcrumb path to a specific section, e.g. ["Chapter 1", "Introduction"]. Use toc_path from a search match, or a child path from expand. Wins over match_id when both are given: match_id is only used when toc_path is absent.
  • context_words — number — Optional future hint for expanding focused reads

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• 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-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.

  Parameters:

  • query (required) — string — The user's question exactly as they asked it. Do not rewrite it.
  • limit — number — Max number of results to return (default 6)
  • short_query — string — Optional. 2-3 words in English that the answering note is sure to contain: the main term and one qualifier, in dictionary form (nominative singular, infinitive). A short phrase, not a list; no punctuation. Keyword search needs every word to match, so fewer precise words beat many.
  • detail_limit — number — How many results include full snippet matches; results beyond this are returned as lightweight previews (title, path, score) to save context (default 3)
  • expected_answer — string — Optional. One or two sentences in English that the answering note itself could contain, written the way the notes state facts (e.g. 'To reset a password, open Settings and select Security.'). Not a description of what the note covers, not a question. If unsure of details, stay general but keep it a statement of fact.
  • rephrased_query — string — Optional. The question asked another way in English: different words, and the canonical name of what it asks about if you know it. One sentence.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• 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.

  Parameters:

  • pid — number — Non-negative integer (uint64) note id, copied verbatim from a search result's note_id field. Not a path, slug, or match_id — a value like ":" or "/hub/goethe.md" is a path, not a note id. Prefer path
  • href — string — String note href, copied verbatim from a search result's href field
  • path — string — String note path, e.g. "concepts/maska-i-glubina.md" — copy verbatim from a search result's note_path field. The default, preferred way to reference a note
  • limit — number — Max number of results (default 10)
  • note_id — number — Same as pid: non-negative integer (uint64) note id, copied verbatim from a search result's note_id field. Not a path, slug, or match_id. Prefer path

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• wiki

  Wiki Knowledge Base Instructions

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

Publisher website Repository

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.