Name: Tether
Author: sidyellur

Tether MCP

Local-first agent memory over SQLite: remember, recall, link, forget. Degrades, never fails.

Grade A Local · stdio API key 4 tools v0.6.1

No reviews yet by sidyellurPyPI 3,049 Runs on your machine, nothing hosted

100/100

trust score

downloads a day

local

runs on your machine

downloads in 30d

What it does

Local-first agent memory over SQLite: remember, recall, link, forget. Degrades, never fails.

Quickstart

# 1 — add it to Claude Code
claude mcp add --scope user sidyellur-tether-mcp '--' uvx tether-memory

# 2 — ask your agent for something these tools do
#   remember, recall, link and 1 more

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

Publisher

sidyellur1 server

1 category

All 1 server

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 Tether 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 uv (docs.astral.sh/uv): uvx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.

claude mcp add --scope user sidyellur-tether-mcp '--' uvx tether-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

Nothing is required, but it can take TETHER_DB (Path to the SQLite memory file. Defaults to the platform data dir (e.g. ~/.local/share/tether/memory.db).), TETHER_SEMANTIC (Set to 0 to force keyword-only recall. Semantic recall needs the [semantic] extra and is on by default when available.), TETHER_SYNC_URL (Optional libSQL/Turso primary URL to sync memory across devices. Leave unset for local-only.), TETHER_SYNC_TOKEN (Auth token for TETHER_SYNC_URL.) if you want to set them.

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

Save a durable memory. UPSERTS: a memory of the same type with the same (whitespace/case-normalized) title is updated in place instead of duplicated, so re-remembering a fact refines it rather than cluttering.

Parameter	Type	Required	Notes
type	string	yes	one of "user", "feedback", "project", "reference".
title	string	yes	a short label; also the dedup key within a type.
body	string	yes	the fact. For feedback/project, a "Why:" / "How to apply:" line helps.
tags	string	no	optional comma-separated tags.
links	array	no	optional list of related memory ids - wired up exactly like calling link() on each one: validated, unioned into both memories' links (never replacing links set earlier, so omitting this on a refine
crystallizes	array	no	optional list of source memory ids this memory abstracts; links it over them as a crystallized principle (needs TETHER_CRYSTALLIZE). Non-integer values, this memory's own id, and ids that don't resolv

Search memories by keyword and semantic similarity, then follow the usage graph to related memories, most relevant first.

Parameter	Type	Required	Notes
query	string	no	free text; punctuation is safe. May be omitted if tags is given.
type	string	no	optional filter ("user"/"feedback"/"project"/"reference").
limit	integer	no	max results (default 20).
budget	integer	no	how far to follow associations (0 = direct matches only).
session	string	no	optional id grouping related recalls so they prime each other.
tags	string	no	optional comma-separated tags; exact-match filter (a memory must carry every listed tag). Combine with query to filter its ranked hits, or use alone (query omitted) to list every current memory with
id	integer	no	fetch this one memory in full instead of searching. Use it after a search returns a truncated hit you want to read completely.
full	boolean	no	return complete bodies for every hit instead of excerpts. Costs the whole payload - prefer id= for the one memory you actually need.

Create a bidirectional link between two memories by id.

Parameter	Type	Required	Notes
id_a	integer	yes	—
id_b	integer	yes	—

Soft-delete a memory by id: marks it no longer current (excluded from recall/the boot index) but keeps the row, reversibly, like consolidation and the forgetting sweep already do. Returns {"forgotten", "existed"}.

Parameter	Type	Required	Notes
id	integer	yes	—

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 Tether or to call it, at any volume.

ATrust score 100 / 100

Release 0.6.1 · scanned 15 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 score100

Findings0 threat · 0 capability

Capabilityminimal

Coveragesource

Verificationsource

Surface digest893ace4ae5add8f8a7e279284f1cf5fe4d22afd3ad06030088c5e7f9a1f9e254

Score vectorthreat 100 → client 100

Term	Level	What it prices	Points
capability-exposure	minimal	capability blast radius (minimal) — client exposure if the model is manipulated	−0
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. minimal is the level these add up to.

Tool	Capability tags	Why the tag was assigned
remember	no tags
recall	untrusted-input	untrusted-input: keyword "fetch"
link	no tags
forget	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 digest893ace4ae5add8f8

Scanned2026-10-15

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.