Name: rutter
Author: shinytoyrobots

rutter MCP

Recall past decisions and the notes your AI sessions cited, from a local markdown folder.

Grade A Local · stdio No auth needed 4 tools v0.9.0 · 20 Oct 2026 MIT

No reviews yet by shinytoyrobotsnpm 453 Runs on your machine, nothing hosted

97/100

trust score

downloads a day

local

runs on your machine

453

downloads in 30d

What it does

Recall past decisions and the notes your AI sessions cited, from a local markdown folder.

Quickstart

# 1 — add it to Claude Code
claude mcp add --scope user --env 'LIBRARIAN_VAULT_PATH=${LIBRARIAN_VAULT_PATH}' --transport stdio rutter-mcp '--' npx -y rutter-memory

# 2 — ask your agent for something these tools do
#   librarian-search, librarian-get-note, librarian-recent and 1 more

It needs LIBRARIAN_VAULT_PATH: this reads it from your environment, so export it first.

rutter costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.

Publishernot claimed

shinytoyrobots1 server

1 category

All 1 server

Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.

Installation

Where are you running it?

Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts rutter as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.

Claude Codedeclared by this listing

This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. Claude Code reads LIBRARIAN_VAULT_PATH (Folder of markdown notes (an Obsidian vault works)) from your environment each time it starts the server, so the value stays out of its config: export it in your shell profile (macOS, Linux), or run setx LIBRARIAN_VAULT_PATH … and open a new terminal (Windows). The '--' is in quotes so that PowerShell passes it on.

claude mcp add --scope user --env 'LIBRARIAN_VAULT_PATH=${LIBRARIAN_VAULT_PATH}' --transport stdio rutter-mcp '--' npx -y rutter-memory

Reconnect, or start a new session, and the tools appear in the model’s tool list.

Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.

What it asks of you

It reaches a system of yours, so it needs settings only you can give it: LIBRARIAN_VAULT_PATH — Folder of markdown notes (an Obsidian vault works). You set it in your own client’s config, on your machine — this marketplace never holds it.

What it writes

One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.

What you approve

4 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.

Tool surface

What the model actually sees. Descriptions are diffed on every release — see version history.

Only tools that write or reach the network

Read from its source code. A server that builds its tool list when it starts can list more tools than this.

Search …'s knowledge vault for notes matching a query. Returns notes ranked by relevance, each with its vault path, type/status/created provenance, and a matching snippet. A result … engaged before also carries a quiet prior-engagement note; report it in plain language for the reader who asked, as…

Parameter	Type	Required	Notes
query	string	yes	What to search for (free text; all terms must match).
limit	integer	no	Max results (default 8).
type	string	no	Filter by frontmatter type (e.g. note, moc, reference).
status	string	no	Filter by frontmatter status (e.g. evergreen, snapshot).
domain	string	no	Filter by frontmatter domain.

Return the full content of one vault note by its path (as returned by librarian-search). Read-only.

Parameter	Type	Required	Notes
path	string	yes	Vault-relative note path, e.g. 'Notes/Reference/foo.md'.

Answer 'what was I working on lately?' from captured session records, newest session first. Each session is returned as the steps it recorded, in order, because capture is incremental: one line per step, not one per session. Report a session as ONE account of what happened, not step by step --…

Parameter	Type	Required	Notes
window	integer	no	Only sessions within the last N days.
count	integer	no	Return at most this many sessions (not steps).
project	string	no	Only sessions from this project (case-insensitive; the name shown in brackets).
detail	string	no	'increments' (default) returns every step; 'brief' returns each session's first and last step only, and says so.

Recall a stance … recorded on a topic (SCN-011). Query one of three ways: 'topic' for an exact topic key (one result or an explicit not-found), 'query' for free text matched against recorded stances (all terms must match), or 'note' for the positions that reference a note by path. Each result is…

Parameter	Type	Required	Notes
topic	string	no	Exact topic key. Returns one topic or an explicit not-found.
query	string	no	Free text matched against recorded stances (all terms must match). Returns a list.
note	string	no	Vault-relative note path; returns the positions whose refs include that note. Returns a list.
chain	boolean	no	Include the full supersession chain for each matched topic (default false: the live position only).

Free

$0 forever

Every tool, no call limit
No card, and mcprush charges nothing for it
Source published under MIT
Runs on your machine — nothing of it reaches our gateway
Nothing to cap, because mcprush bills nothing

Nothing here is billable: mcprush charges nothing to install rutter or to call it, at any volume.

ATrust score 97 / 100

Release 0.9.0 · scanned 20 Oct 2026

Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.

Threat score100

Client score97

Findings1 threat · 0 capability

Capabilitymoderate

Coveragesource

Verificationsource

Surface digeste4ad467130bb113a86ef1c68bbb1cea1bb3eb30f49855d5d515428622762fd13

Score vectorthreat 100 → client 97

Term	Level	What it prices	Points
capability-exposure	moderate	capability blast radius (moderate) — client exposure if the model is manipulated	−3
verification-discount	source	publisher verification (provenance) — cryptographic build provenance ties the artifact to its source	−0
coverage-honesty	source	inspection depth (source) — how much of the target the scan could see	−0

score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.

What the scan could actually read

A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.

Tool surfaceread

Implementation sourceread

Package metadataread

Live transportnot available

Tools were statically extracted from the published source (4 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".

Capability — what it could do if the model were manipulated

Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.

Tool	Capability tags	Why the tag was assigned
librarian-search	no tags
librarian-get-note	no tags
librarian-recent	no tags
librarian-positions	no tags

Toxic-flow graph

The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.

The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.

Supply chain and provenance

Integrityfirst-seen

Surface digeste4ad467130bb113a

Scanned2026-10-20

This is the first scan of this surface here, so there is nothing yet to compare it against.

Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.