Local MCP capabilities provider for Expo
Cryptoseed 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
Cryptography tools for AI agents: ChaCha20-Poly1305, X25519, Ed25519. Keys in system Keychain. HTTP/HTTPS transport for remote agents. macOS, Linux, Windows.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user cryptoseed-mcp '--' npx -y cryptoseed-mcp
# 2 — ask your agent for something these tools do
# key_new, key_list, identity_new and 24 more
Cryptoseed costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
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 Cryptoseed 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. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user cryptoseed-mcp '--' npx -y cryptoseed-mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
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.
27 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.
Generate a new 256-bit symmetric encryption key and save it to the macOS Keychain.
No parameter schema on file.
List all symmetric keys stored in the Keychain.
No parameter schema on file.
Generate a new X25519 keypair. Private key goes to Keychain, public key is printed for sharing.
No parameter schema on file.
Print the public key of an identity as base64. Share this with anyone who wants to send you encrypted messages.
No parameter schema on file.
List all X25519 identities stored in the Keychain.
No parameter schema on file.
Save a contact\
No parameter schema on file.
Update a contact\
No parameter schema on file.
Return full contact record as JSON: pubkey, channels, and notes.
No parameter schema on file.
List all saved contacts.
No parameter schema on file.
Retrieve a saved contact\
No parameter schema on file.
Remove a contact.
No parameter schema on file.
Add a second (or further) public key to an existing contact. Supports X25519 keys (for encrypt_asym) and Ed25519 keys (for signature verification).
No parameter schema on file.
Export all contacts as a portable .cryptoseedcontacts bundle. The file can be imported into the CryptoSeed iOS app or another MCP instance.
No parameter schema on file.
Import contacts from a .cryptoseedcontacts bundle file. New contacts are added; existing contacts have new keys merged in (no duplicates).
No parameter schema on file.
Encrypt a text string with a symmetric key. Returns a base64 ciphertext.
No parameter schema on file.
Decrypt a base64 ciphertext with a symmetric key. Returns the original plaintext.
No parameter schema on file.
Encrypt a file with a symmetric key. Produces a .seed file compatible with the CryptoSeed iOS app.
No parameter schema on file.
Decrypt a .seed file with a symmetric key. Restores the original file.
No parameter schema on file.
Encrypt a message to a recipient\
No parameter schema on file.
Decrypt a message encrypted to your X25519 identity. Use this to read messages sent to you via encrypt_asym.
No parameter schema on file.
Generate a new Ed25519 keypair for signing. Private key goes to Keychain, public key is stored on disk. Compatible with CryptoSeed iOS signing keys.
No parameter schema on file.
List all Ed25519 signing key aliases stored in the Keychain.
No parameter schema on file.
Get the public key of a signing key as base64. Share this so others can verify your signatures.
No parameter schema on file.
Sign a text string with an Ed25519 signing key. Returns a CSS-SIG-1 proof JSON object compatible with the CryptoSeed iOS app.
No parameter schema on file.
Sign a file with an Ed25519 signing key. Returns a CSS-SIG-1 proof JSON object compatible with the CryptoSeed iOS app.
No parameter schema on file.
Verify a text string against a CSS-SIG-1 proof. Returns signature validity and signer trust level. Accepts proof as raw JSON or base64-encoded JSON.
No parameter schema on file.
Verify a file against a CSS-SIG-1 proof. Returns signature validity and signer trust level. Accepts proof as raw JSON or base64-encoded JSON.
No parameter schema on file.
- 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 Cryptoseed 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 | minimal | capability blast radius (minimal) — client exposure if the model is manipulated | −0 |
| 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 (27 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 |
|---|---|---|
| key_new | no tags | |
| key_list | no tags | |
| identity_new | no tags | |
| identity_pubkey | no tags | |
| identity_list | no tags | |
| contact_add | no tags | |
| contact_update | no tags | |
| contact_info | no tags | |
| contact_list | no tags | |
| contact_pubkey | no tags | |
| contact_remove | no tags | |
| contact_key_add | no tags | |
| contact_export | no tags | |
| contact_import | no tags | |
| encrypt_text | no tags | |
| decrypt_text | no tags | |
| encrypt_file | no tags | |
| decrypt_file | no tags | |
| encrypt_asym | no tags | |
| decrypt_asym | untrusted-input | untrusted-input: keyword "read_message" |
| signing_key_new | no tags | |
| signing_key_list | no tags | |
| signing_key_pubkey | no tags | |
| sign_text | no tags | |
| sign_file | no tags | |
| verify_text | no tags | |
| verify_file | 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
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 1.3.0. 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 Cryptoseed 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.