Official Infisical MCP Server
Nothing to run from here
Bitwarden 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.
94/100
trust score
443
downloads a day
local
runs on your machine
17
tools declared
What it does
Give your assistant its own Bitwarden vault for logins, passwords, 2FA codes and passkeys.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --env 'BITWARDEN_CLIENT_ID_FILE=${BITWARDEN_CLIENT_ID_FILE}' --env 'BITWARDEN_CLIENT_SECRET_FILE=${BITWARDEN_CLIENT_SECRET_FILE}' --env 'BITWARDEN_MASTER_PASSWORD_FILE=${BITWARDEN_MASTER_PASSWORD_FILE}' --transport stdio foreverworks-bitwarden-mcp '--' npx -y @foreverworks/mcp-bitwarden
# 2 — ask your agent for something these tools do
# health, find_logins, get_login and 14 more
It needs BITWARDEN_CLIENT_ID_FILE, BITWARDEN_CLIENT_SECRET_FILE, BITWARDEN_MASTER_PASSWORD_FILE: this reads them from your environment, so export them first.
Bitwarden costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publisher
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Bitwarden as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. Claude Code reads BITWARDEN_CLIENT_ID_FILE (Path of a file holding the account's API key client id), BITWARDEN_CLIENT_SECRET_FILE (Path of a file holding the API key's client secret), BITWARDEN_MASTER_PASSWORD_FILE (Path of a file holding the master password that unlocks the vault) from your environment each time it starts the server, so the value stays out of its config: export them in your shell profile (macOS, Linux), or run setx BITWARDEN_CLIENT_ID_FILE …, setx BITWARDEN_CLIENT_SECRET_FILE …, setx BITWARDEN_MASTER_PASSWORD_FILE … and open a new terminal (Windows). The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user --env 'BITWARDEN_CLIENT_ID_FILE=${BITWARDEN_CLIENT_ID_FILE}' --env 'BITWARDEN_CLIENT_SECRET_FILE=${BITWARDEN_CLIENT_SECRET_FILE}' --env 'BITWARDEN_MASTER_PASSWORD_FILE=${BITWARDEN_MASTER_PASSWORD_FILE}' --transport stdio foreverworks-bitwarden-mcp '--' npx -y @foreverworks/mcp-bitwardenReconnect, 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 your own credential rather than the publisher’s: BITWARDEN_CLIENT_ID_FILE — Path of a file holding the account's API key client id.; BITWARDEN_CLIENT_SECRET_FILE — Path of a file holding the API key's client secret.; BITWARDEN_MASTER_PASSWORD_FILE — Path of a file holding the master password that unlocks the vault.. You set them 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
17 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.
Check that the vault is reachable and unlocked, and say as whom: the account, the server, when it last synced, how many
No parameter schema on file.
Search the vault's logins and secure notes (kind says which). search matches name, username and URL; url finds
| Parameter | Type | Required | Notes |
|---|---|---|---|
| search | string | no | Words in the name, username or URL. |
| url | string | no | The site's URL, e.g. https://github.com/login; its host is what find_logins' url matches. |
| limit | integer | no | Return at most this many; count says how many matched. |
One login or secure note in full except its secrets: name, username, URLs, collections, notes, custom fields (hidden
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | The item id, from find_logins. |
The login's password, with its username and URLs, for typing into the site. Use it only for that: never write it into
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | The item id, from find_logins. |
| previous | boolean | no | Return the password before the current one instead. |
One custom field's value, hidden ones included, from a login or a secure note: a secret that is not a password, such
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | The item id, from find_logins. |
| field | string | yes | The field's name as get_login lists it (case does not matter). |
The login's current authenticator (TOTP) code and how many seconds it stays valid, computed from the key stored on
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | The item id, from find_logins. |
Whether a login's password appears in Have I Been Pwned's list of passwords seen in data breaches, and how many
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | The item id, from find_logins. |
| previous | boolean | no | Check the password before the current one instead. |
Save a new login. Without password or password_file a strong one is generated here and stored; nothing returns it,
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | What the account is, e.g. 'GitHub (example-bot)'. |
| url | string | no | The site's URL, e.g. https://github.com/login; its host is what find_logins' url matches. |
| username | string | no | The login name or email the site knows the account by. |
| password | string | no | — |
| password_file | no | — | |
| length | integer | no | Length of a generated password. Default 24. |
| symbols | boolean | no | Whether a generated password contains symbols (!@#$%^&*-_=+). Default true; turn off for sites that refuse them. |
| notes | string | no | Free text kept with the login: recovery codes, security answers, what the account is for. |
| totp_secret | string | no | — |
| collection | string | no | A collection name from health. Default: …. |
Change a login: only what is named changes. rotate_password generates a new password and stores it at once; change it
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | The item id, from find_logins. |
| name | string | no | A new name. |
| url | string | no | The site's URL, e.g. https://github.com/login; its host is what find_logins' url matches. |
| username | string | no | The login name or email the site knows the account by. |
| password | string | no | — |
| password_file | no | — | |
| rotate_password | boolean | no | Generate a new password (with length and symbols). |
| length | integer | no | Length of a generated password. Default 24. |
| symbols | boolean | no | Whether a generated password contains symbols (!@#$%^&*-_=+). Default true; turn off for sites that refuse them. |
| notes | string | no | Replaces the notes. |
| append_notes | string | no | Added after the current notes on a new line; nothing is lost. |
| totp_secret | string | no | — |
| replace_totp | boolean | no | Replace a DIFFERENT authenticator key the login already has (or clear it with an empty totp_secret). |
Save a secret that is not a login as a new secure note: a service account's key file, an API token, a licence key.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | What the secret is, e.g. 'Play service account key (example-app)'. |
| fields | array | yes | The secrets, one field each, and any plain details beside them. |
| notes | string | no | Plain text anyone reading the note sees (get_login shows it): what the secret is for, where it is used. Never the secret itself. |
| collection | string | no | A collection name from health. Default: …. |
Put a login or secure note in one collection: its collections become exactly the one named. Only between the
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | The item id, from find_logins. |
| collection | string | yes | The collection to put it in: its name as health lists it (case does not matter), or its id. |
Pull the vault from Bitwarden now. Reads already sync every 30 seconds; this is for right after someone changed something in the web vault.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
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
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Bitwarden or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 94 / 100
Release 0.2.1 · scanned 3 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 score94
Findings1 threat · 0 capability
Capabilityhigh
Coveragesource
Verificationsource
Surface digestedcda3165b962a24fdf1e7cecb036c13d81c21c6529e7fc5eb412bdf5c64b461
Score vectorthreat 100 → client 94
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| 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 (17 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. high is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| list_passkeys | no tags | |
| create_passkey | no tags | |
| assert_passkey | no tags | |
| import_passkeys | no tags | |
| delete_passkey | state-write | state-write: declares destructiveHint: true |
| health | no tags | |
| find_logins | no tags | |
| get_login | no tags | |
| get_password | no tags | |
| get_field | no tags | |
| totp | no tags | |
| check_exposed | no tags | |
| create_login | no tags | |
| update_login | no tags | |
| create_note | no tags | |
| move_item | no tags | |
| sync | 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 digestedcda3165b962a24
Scanned2026-11-03
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 0.2.1. Pin a release below and the command asks for exactly that one.
0.2.1
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
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.
Sign in to write one
Any signed-in account that does not publish Bitwarden can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
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.