Model Context Protocol (MCP) server for freee API integration
Sellat is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
What it does
Proof of existence for files from any MCP client: hashed locally, anchored on Polygon and Bitcoin.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --env 'SELLAT_API_TOKEN=${SELLAT_API_TOKEN}' --transport stdio sellat-mcp '--' npx -y sellat-mcp
# 2 — ask your agent for something these tools do
# sellat_hash, sellat_find, sellat_stamp and 6 more
It needs SELLAT_API_TOKEN: this reads it from your environment, so export it first.
Sellat costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Sellat as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. Claude Code reads SELLAT_API_TOKEN (Your Sellat API key (sellat_…), from sellat.app → Dashboard → API) from your environment each time it starts the server, so the value stays out of its config: export it in your shell profile (macOS, Linux), or run setx SELLAT_API_TOKEN … and open a new terminal (Windows). The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user --env 'SELLAT_API_TOKEN=${SELLAT_API_TOKEN}' --transport stdio sellat-mcp '--' npx -y sellat-mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
It reaches a system of yours, so it needs your own credential rather than the publisher’s: SELLAT_API_TOKEN — Your Sellat API key (sellat_…), from sellat.app → Dashboard → API. You set it in your own client’s config, on your machine — this marketplace never holds it.
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.
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.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
Compute the SHA-256 fingerprint of a local file. Runs entirely on this machine: nothing is sent anywhere. Useful to compare two files or to check a fingerprint someone gave you.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| path | string | yes | Absolute path of the file (~ is expanded). |
Find files on this computer by name, in the user's Downloads, Desktop, Documents and Pictures folders (their real names on this system), newest first. Reads names only, never contents. Use it whenever the user refers to a file without giving its path. With no query it lists the most recent files.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | no | Words from the file name, any order, case and accents ignored ("contrato alquiler", "pdf"). |
| where | string | no | Which folder to search. Default all four. |
| folder | string | no | Search this folder instead (absolute path, ~ expanded). |
| modified_within_days | number | no | Only files changed in the last N days ("yesterday" = 2). |
Create a SELLAT proof of existence for a local file. The file is hashed on this machine and only its SHA-256 (plus the name and size) is sent; the file itself never leaves the computer. Stamping the same file again returns the existing proof (the earlier date is the stronger one). Set…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| path | string | yes | Absolute path of the file to protect (~ is expanded). |
| name | string | no | Name shown on the certificate. Defaults to the file name. |
| qualified | boolean | no | Also issue the qualified timestamp (eIDAS). Spends one seal. Only if the user asked for it. |
The current state of a proof: whether its batch is anchored on Polygon, the Bitcoin confirmation, the qualified seal and its URLs.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| proof_id | string | yes | The SELLAT proof id (returned by sellat_stamp or sellat_list). |
The account's proofs, newest first, one page at a time.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| limit | integer | no | Page size, 1–100 (default 25). |
| cursor | string | no | next_cursor from the previous page. |
Issue the qualified electronic timestamp (eIDAS, RFC 3161) for an existing proof. Spends one seal from the account: call it only when the user explicitly asked for it. With no seals left it returns the link to buy them on the web. Calling it again on a sealed proof returns the existing seal…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| proof_id | string | yes | The SELLAT proof id (returned by sellat_stamp or sellat_list). |
The account's plan, qualified seals remaining, custody usage and today's proof budget, with the link to buy seals.
No parameter schema on file.
Save a proof document to this computer: the PDF certificate, the evidence package (ZIP with proof.json, the OpenTimestamps file and instructions to verify without SELLAT) or the RFC 3161 token of the qualified seal (.tsr). Never overwrites an existing file.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| proof_id | string | yes | The SELLAT proof id (returned by sellat_stamp or sellat_list). |
| kind | string | yes | certificate = PDF, evidence = ZIP package, tsr = qualified seal token. |
| lang | string | no | Language of the certificate or package; use the user's language. Default en. |
| directory | string | no | Folder to save into. Default: SELLAT_DOWNLOAD_DIR, else ~/Downloads. |
Check that a file matches a SELLAT proof and that the proof is really anchored on the blockchain, without trusting SELLAT: the file is hashed locally, the Merkle path is recomputed, and a public blockchain node is asked whether the anchoring transaction carries the root. Give the proof as a…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| file_path | string | yes | Absolute path of the file to check. |
| proof_path | string | no | Path to proof.json or to an evidence package (.zip). |
| proof_id | string | no | A proof id, when there is no proof file at hand. |
| offline | boolean | no | Skip the blockchain check (math only): proves no date. Default false. |
- 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
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Sellat or to call it, at any volume.
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.
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
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.
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 |
|---|---|---|
| sellat_hash | no tags | |
| sellat_find | no tags | |
| sellat_stamp | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| sellat_status | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| sellat_list | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| sellat_seal | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| sellat_account | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| sellat_download | untrusted-inputexternal-sink | untrusted-input: keyword "download"; external-sink: declares readOnlyHint: false, openWorldHint: true |
| sellat_verify | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
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.
Supply chain and provenance
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.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 0.3.3. Pin a release below and the command asks for exactly that one.
No release note was published with this version.
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Any signed-in account that does not publish Sellat can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.