Name: Sniptide
Author: Dino-Kupinic

Sniptide MCP

Search and manage your Sniptide snippets.

Grade A Remote or local · Streamable HTTP · stdio API key 9 tools v0.5.0 · 4 Nov 2026 AGPL-3.0

No reviews yet by Dino-Kupinicnpm 2,083 Runs on your machine or at its publisher’s address — not through us

97/100

trust score

324

downloads a day

local

or remote

downloads in 30d

What it does

Search and manage your Sniptide snippets.

Quickstart

# 1 — add it to Claude Code
claude mcp add --scope user --env 'SNIPTIDE_TOKEN=${SNIPTIDE_TOKEN}' --transport stdio sniptide-mcp '--' npx -y @sniptide/mcp

# 2 — ask your agent for something these tools do
#   search_snippets, read_snippet, fetch_collection and 6 more

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

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

Publisher

Dino-Kupinic1 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 can run either way — at an address its publisher runs, or as a process under your own user, with your files and your network — and this marketplace is in the path of neither.

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 SNIPTIDE_TOKEN (Personal API token) 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 SNIPTIDE_TOKEN … and open a new terminal (Windows). The '--' is in quotes so that PowerShell passes it on.

claude mcp add --scope user --env 'SNIPTIDE_TOKEN=${SNIPTIDE_TOKEN}' --transport stdio sniptide-mcp '--' npx -y @sniptide/mcp

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

Or connect to its publisher’s address

Its publisher also runs it at https://app.sniptide.com/api/mcp: nothing to start on your machine, and this marketplace is not in the path.

claude mcp add --scope user --transport http sniptide-mcp https://app.sniptide.com/api/mcp

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 your own credential rather than the publisher’s: SNIPTIDE_TOKEN — Personal API token. 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

9 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.

Find your live snippets by words in the title, description, tags, file paths or code (every word must match), plus tag, language and collection filters. Returns summaries and nextCursor; call again with that cursor for the next page. Use read_snippet to fetch code.

Parameter	Type	Required	Notes
query	string	no	—
tags	array	no	—
language	string	no	—
collection	string	no	—
limit	integer	no	—
cursor	string	no	—

Read one of your live snippets by its ID or slug, including all files, paths, code and source metadata.

Parameter	Type	Required	Notes
id	string	yes	—

Fetch a page of your collection as numbered recipe steps, with full snippet files. Order is oldest capture first, matching the CLI. Continue with nextCursor and nextStep; a page holds up to 50 snippets. This does not execute the recipe.

Parameter	Type	Required	Notes
slug	string	yes	—
cursor	string	no	—
startStep	integer	no	—

Save code as a new snippet (write scope required). Defaults to private. A collection must already exist. Up to 10 files; instance size and storage limits apply. Files are data only. Do not retry automatically: retries may create duplicates.

No parameter schema on file.

Replace the title and entire file list of your live snippet (write scope required). Read it first to keep files you still need. Omitted description, visibility, collection, tags and source are preserved; explicit null clears collection/source. Link, expiry, password and burn setting remain…

Parameter	Type	Required	Notes
id	string	yes	—

List your collections, oldest first, with each slug, name and live snippet count. Use a slug as the collection of create_snippet, update_snippet or fetch_collection.

No parameter schema on file.

Create an empty collection by name (write scope required) and return its slug. Names are unique per account and accounts hold up to 50 collections. Renaming and deleting collections stay in the app.

Parameter	Type	Required	Notes
name	string	yes	—

Change who can open your live snippet (write scope required): visibility, expiry counted from now, a password (null removes it) and burn after read. Omitted fields stay as they are. Confirm with the user before making a snippet public or setting a password, which is then visible in this…

Parameter	Type	Required	Notes
id	string	yes	—

Move your live snippet to the trash (write scope required). Its link stops working; the owner can restore it from the app until the trash is emptied. This tool never deletes permanently. Confirm with the user first.

Parameter	Type	Required	Notes
id	string	yes	—

Free

$0 forever

Every tool, no call limit
No card, and mcprush charges nothing for it
Source published under AGPL-3.0
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 Sniptide or to call it, at any volume.

ATrust score 97 / 100

Release 0.5.0 · scanned 5 Nov 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

Findings0 threat · 0 capability

Capabilitymoderate

Coveragesource

Verificationsource

Surface digest8532221d4e256732326a320d45ba8925d136e951b9e636babfb7da70c0cb9205

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 (9 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
search_snippets	untrusted-input	untrusted-input: keyword "fetch"
read_snippet	no tags
fetch_collection	untrusted-input	untrusted-input: keyword "fetch"
create_snippet	state-write	state-write: declares readOnlyHint: false
update_snippet	state-write	state-write: declares readOnlyHint: false, destructiveHint: true
list_collections	no tags
create_collection	state-write	state-write: declares readOnlyHint: false
update_snippet_settings	state-write	state-write: declares readOnlyHint: false, destructiveHint: true
trash_snippet	state-write	state-write: declares readOnlyHint: false, destructiveHint: true

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 digest8532221d4e256732

Scanned2026-11-05

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.