Explicit Formula — Second Brain

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/travisbergen2-second-brain

About

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.

Tools

12 read · 1 write · 0 delete · 1 not yet classified

Secrets

None asked for

Install scripts

Not scanned yet

Runs as

Node.js package

Tools (14)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

• calibrate_profileCalibrate a user’s receiver profileread-only

  Build a ReceiverProfile (TI, SG, FT, UE, AR — continuous 0-100, never a category label) from five behavioral forced-choice answers. Call with NO answers to get the five questions to ask the user; call again with their answers (a/b/c per primitive) to get the profile. Store the returned profile JSON in the user’s notes or memory and pass it to render_reply / prepare_prompt on every turn. Deterministic and stateless — nothing is stored server-side. Schema: https://rpcs1.dev/v1/receiver-profile.json

• forkFork view — how could this message read?read-only

  The calibrated ambiguity surface: deterministic structural fork detectors (reference, scope, grouping, compare-vs-choose, polysemy) with character-offset spans, plus per-reading one-line clarifiers the sender can append to lock a reading in. Returns competing readings, an ask-back question, and a forked-answer scaffold. Silent on clean text by contract. Runs the deterministic mirror floor only over MCP (no model). Prefer this over interpret for span-level ambiguity detection: interpret’s entity list is a word-list engine (calibrated 2026-08-15: no discrimination on conversational text) — advis…

• interpretInterpret ambiguous human inputread-only

  Detect ambiguity in a user message and score candidate interpretations using the RPCS-1 Signature Ambiguity Framework. Returns literal summary, implied meaning, confidence, AR level (AR0-AR5), ambiguities, clarifying questions, and per-candidate scores (IC, UE, EC, NM, SG, TI). Use when a user says something vague, passive-aggressive, or underspecified.

• list_second_brainList available notesread-only

  List the notes the user has allowed (metadata only: path, title, last-modified date — no content). Newest first, up to 200. Optional folder filter. Use it to browse before reading.

• normalizeNormalize fragmented human inputread-only

  Clean up text with ellipses, fragments, and run-on thoughts into coherent prose. Returns the number of fragments detected and the joined version. Use when a user types stream-of-consciousness or fragmented input.

• prepare_promptPrepare a user’s message before acting on itread-only

  The inbound half of the Translation Bridge loop. Takes the user’s raw message (possibly ambiguous, fragmented, or underspecified) plus their ReceiverProfile, and returns the recovered intent, a canonical translation to act on, ambiguity level, and — profile-aware — whether to clarify or commit. Call this before acting on any ambiguous user request. Scope note: its detectors are lexical/structural (vague signals, ambiguous references) — for the commit-vs-clarify DECISION, route_intent (with your own proposed readings) is the authority; when they disagree, follow route_intent.

• read_second_brain_noteRead one noteread-only

  Read a single note by its vault path (as returned by search or list). Returns up to 8000 characters per call; when truncated, call again with the offset the result gives you. Only notes inside the user's allowed folders can be read.

• recommend_agent_configurationRecommend AI agent configurationread-only

  Diagnose why a deployed AI agent may fail. Takes environmental entropy, predictability, stakes, context horizon, and commitment style, then returns receiver profile values (TI, SG, FT, UE, AR), platform parameters (temperature, top_p, strategy), regime prediction, reasoning, and warnings. Optionally pass target_model to attach MEASURED per-model receiver posture (E-LIT table). Deterministic, stateless, read-only — does not store past recommendations.

• render_replyRender a reply for a specific user’s receiver profileread-only

  The outbound half of the Translation Bridge loop. Takes your draft reply plus the user’s ReceiverProfile and returns deterministic rendering instructions (structure, warmth, explicitness, revision posture, ambiguity handling — each with a why-trace). Apply the instructions to your draft before answering. Call this on every reply to a calibrated user.

• report_perception

  Report the perceived readings of the user message.

• rewriteRewrite text for a target audienceread-only

  Get rewrite instructions for adapting text to a specific audience style: technical, plain, socially_gentle, concise, detailed, or direct. Pass the result to an LLM with the rewrite_instructions as the system prompt. Use when communication needs tone adjustment.

• route_intentRoute an ambiguous request: commit, present options, or clarifyread-only

  Entropy routing over competing interpretations — the model proposes, the deterministic core disposes. YOU generate the candidate readings of the user’s message (3–7 short hypotheses covering the plausible interpretations, INCLUDING likely-typo readings, idiom-vs-literal readings, and domain senses) and pass them as hypotheses, ideally with your own likelihoods (0–1 per reading) AND a paraphrase per reading — the user’s message rewritten unambiguously under that interpretation, so the user can VERIFY intent by recognition before anything commits (one misread prompt skews a whole thread). The ro…

• save_to_second_brainSave a note to the second brain

  Save a NEW note into the user's second brain — only when the user asks to keep something. Writes only into their write-back folder (never elsewhere), never overwrites, and wikilinks the source notes you pass — so the note appears in their Obsidian graph connected to the knowledge it used. Pass the vault paths you actually drew from as sources.

• search_second_brainSearch the second brainread-only

  Search the user's own notes for context relevant to the task. Returns up to 6 short snippets (≤2400 chars total) chosen by a deterministic local scorer (their words × their note titles/headings × recency), each labeled with its source note path — cite those paths. Every snippet returned is disclosed to the user. Use plain topical words (as the user would title a note), not full sentences.

Signals

Stars

0

Forks

0

Open issues

0

Last commit

Oct 21, 2026 (8 days ago)

Last release

Sep 1, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

Registry name

io.github.travisbergen2/second-brain

Version

0.1.0

Auth

No auth

Packages

npm @travisbergen2/second-brain-mcp

License

MIT

Repository

github.com/travisbergen2/rpcs1-sdk

Website

www.explicitformula.com

First seen

Oct 24, 2026

Last checked

Oct 24, 2026

Source

Official MCP Registrygithub-graphql