The official Svelte MCP server providing docs and autofixing tools for Svelte development
Nothing to run from here
Venira 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
44
tools declared
local
runs on your machine
—
downloads a day
What it does
Workspace-scoped MCP server for coding agents: files, search, shell, checkpoints, PR/CI, audit.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user venira-mcp '--' npx -y venira-mcp
# 2 — ask your agent for something these tools do
# project_pr_create, project_pr_comment, project_pr_merge and 41 more
Venira costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
N0All 1 server
n0moreher01 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
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 Venira 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. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user venira-mcp '--' npx -y venira-mcpReconnect, 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 VENIRA_WORKSPACE (Absolute path of the project folder the server works in. Defaults to the current directory.), VENIRA_DATA_DIR (Folder for the audit database and encrypted secrets. Defaults to <workspace>/data.) 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
44 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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| title | string | yes | PR title (imperative, one line). |
| head | string | no | Source branch (default: the current branch). |
| base | string | no | Target branch (default: the repository default branch). |
| body | string | no | PR description (markdown); usually a summary + test plan. |
| draft | no | 1 opens as a draft PR; 0 opens as ready for review. | |
| repo | string | no | "owner/name" or PR URL. Default: configured repo or git origin. |
| provider | string | no | Default: configured, else from git origin. |
| reason | yes | — |
| Parameter | Type | Required | Notes |
|---|---|---|---|
| pr | yes | PR number or PR URL. | |
| body | string | yes | Comment body (markdown). |
| path | string | no | Workspace/repo file path for an inline review comment (requires line); omit for a general comment. |
| line | integer | no | Line number to anchor the inline note (new side by default). |
| start_line | integer | no | First line of a multi-line inline note (must be <= line; GitHub/GitLab). |
| side | string | no | RIGHT = new code (default), LEFT = deleted code. |
| commit_id | string | no | Commit sha the note is anchored to (default: the PR head). |
| repo | string | no | "owner/name" or PR URL. Default: configured repo or git origin. |
| provider | string | no | Default: configured, else from git origin. |
| reason | yes | — |
| Parameter | Type | Required | Notes |
|---|---|---|---|
| pr | yes | PR number or PR URL. | |
| method | string | no | Merge strategy (default: merge). |
| commit_title | string | no | Title for the merge commit (squash/merge). |
| commit_message | string | no | Body for the merge commit. |
| delete_branch | no | 1 deletes the head branch after a successful merge (same-repo only); 0 keeps it. | |
| repo | string | no | "owner/name" or PR URL. Default: configured repo or git origin. |
| provider | string | no | Default: configured, else from git origin. |
| reason | yes | — |
| Parameter | Type | Required | Notes |
|---|---|---|---|
| state | string | no | Filter by state (default: open). |
| head | string | no | Filter by source/head branch. |
| base | string | no | Filter by target/base branch. |
| limit | integer | no | Max PRs to return (default 20, cap 100). |
| repo | string | no | "owner/name" or PR URL. Default: configured repo or git origin. |
| provider | string | no | Default: configured, else from git origin. |
| Parameter | Type | Required | Notes |
|---|---|---|---|
| pr | yes | PR number or PR URL. | |
| repo | string | no | "owner/name" or PR URL. Default: configured repo or git origin. |
| provider | string | no | Default: configured, else from git origin. |
| reason | yes | — |
| Parameter | Type | Required | Notes |
|---|---|---|---|
| pr | yes | PR number or PR URL. | |
| repo | string | no | "owner/name" or PR URL. Default: configured repo or git origin. |
| provider | string | no | Default: configured, else from git origin. |
| reason | yes | — |
| Parameter | Type | Required | Notes |
|---|---|---|---|
| run_id | no | Inspect one run: GitHub/GitLab numeric id, or a Bitbucket pipeline UUID. | |
| ref | string | no | Commit sha or branch: read check-runs (GitHub) or the newest pipeline for that ref. |
| pr | no | PR number or PR URL: read check-runs for the PR head commit. | |
| branch | string | no | Filter runs by branch. |
| workflow | string | no | Workflow file name (ci.yml) or numeric id. |
| limit | integer | no | Max runs (or check-runs) to list (default 10 / 20). |
| repo | string | no | "owner/name" or PR URL. Default: configured repo or git origin. |
| provider | string | no | Default: configured, else from git origin. |
| Parameter | Type | Required | Notes |
|---|---|---|---|
| action | string | yes | Cancel the selected run, or retry only failed/canceled jobs if supported. |
| run_id | yes | Exact provider run ID from project_ci_status; Bitbucket uses a pipeline UUID. | |
| repo | string | no | "owner/name" or PR URL. Default: configured repo or git origin. |
| provider | string | no | Default: configured, else from git origin. |
| reason | string | yes | Why this CI action is needed; recorded in the audit trail, secrets redacted. |
| Parameter | Type | Required | Notes |
|---|---|---|---|
| workflow | string | no | GitHub: workflow file name (ci.yml) or id (required). GitLab: optional label. Bitbucket: custom pipeline pattern (default: default). |
| ref | string | no | Branch/tag to run on (default: current branch, else default branch). |
| inputs | object | no | — |
| repo | string | no | "owner/name" or PR URL. Default: configured repo or git origin. |
| provider | string | no | Default: configured, else from git origin. |
| reason | yes | — |
| Parameter | Type | Required | Notes |
|---|---|---|---|
| run_id | no | Whole run: GitHub/GitLab id, or a Bitbucket pipeline UUID. | |
| job_id | no | Single job: GitHub/GitLab job id, or a Bitbucket step UUID (or "pipelineUuid:stepUuid"). | |
| tail_lines | integer | no | Keep only the last N lines (default 500). |
| max_bytes | integer | no | Max text bytes returned (default 512KB, cap 4MB). |
| repo | string | no | "owner/name" or PR URL. Default: configured repo or git origin. |
| provider | string | no | Default: configured, else from git origin. |
| Parameter | Type | Required | Notes |
|---|---|---|---|
| run_id | no | Wait on one run: GitHub/GitLab numeric id, or a Bitbucket pipeline UUID. | |
| ref | string | no | Commit sha or branch: wait on check-runs (GitHub) or the newest pipeline. |
| pr | no | PR number or URL: wait on its head-sha check-runs. | |
| branch | string | no | Wait on the newest run/pipeline for this branch (optionally narrow with workflow). |
| workflow | string | no | Workflow file name (ci.yml) or numeric id; narrows a branch selector. |
| until | string | no | Stop at a terminal state (default) or on the first state change. |
| timeout_ms | integer | no | Max wait in ms (default 45_000, max 110_000). Values > ~55 s need a client request timeout > 60 s. |
| interval_ms | integer | no | Poll interval in ms (default 5000; min 2000, max 15000). |
| include_failure_tail | no | 1 fetches the failing job/run log tail on failure (default); 0 skips it. | |
| tail_lines | integer | no | Failure tail lines (default 80). |
| repo | string | no | "owner/name" or PR URL. Default: configured repo or git origin. |
| provider | string | no | Default: configured, else from git origin. |
| Parameter | Type | Required | Notes |
|---|---|---|---|
| action | string | yes | — |
| replace_existing | no | action=start: 1 explicitly authorizes replacing an existing GitHub credential; 0 does not. | |
| pending_id | string | no | action=poll: opaque id returned by action=start; it does not contain the device code or token. |
| Parameter | Type | Required | Notes |
|---|---|---|---|
| action | string | no | — |
| name | string | no | Env-var style name, e.g. GITHUB_TOKEN (required for get/set/delete). |
| value | string | no | Secret value for action=set. Prefer value_env so it never appears in the transcript. |
| value_env | string | no | Read the value from this host environment variable instead of value (never logged). |
| expires_in_days | integer | no | action=set: expiry in days (e.g. 90 for quarterly rotation). Expired secrets are not injected. |
| expires_at | no | action=set: absolute expiry (epoch ms or ISO-8601), instead of expires_in_days. | |
| reveal | no | action=get: 1 returns the plaintext value and requires VENIRA_SECRET_ALLOW_REVEAL=1 on the host; prefer secret_env injection. | |
| reason | yes | — |
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.
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.
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.
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.
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.
No parameter schema on file.
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
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Venira 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 1.19.0 · scanned 9 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
Findings16 threat · 18 capability
Capabilityhigh
Coveragesource
Verificationsource
Surface digeste40f6347103260397eea2b1789a47d13c7467e96ac0c2e16daefb73e4e48bd2c
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 (44 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>".
1 of the 44 recovered tools are registered only when ALLOW_JS_EXEC holds (dist/tools/project-register-ops.js:54) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes only the other 43.
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.
43 tools are registered unconditionally · 1 more only when ALLOW_JS_EXEC holds (dist/tools/project-register-ops.js:54) — typically when a key or option is configured. All 44 are in the table below and were analysed; the conditional ones are marked.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| project_outline_symbol | no tags | |
| project_diff_files | no tags | |
| project_symbol_references | no tags | |
| project_selective_search | no tags | |
| project_dependency_graph | no tags | |
| project_change_impact | no tags | |
| project_list_files | sensitive-source | sensitive-source: keyword "list_files" |
| project_read_file | sensitive-source | sensitive-source: keyword "read_file" |
| project_get_file_info | no tags | |
| project_search | no tags | |
| project_recent_files | no tags | |
| project_read_batch | no tags | |
| project_write_file | file-write | file-write: keyword "write_file" in tool name |
| project_edit_file | file-write | file-write: keyword "edit_file" in tool name |
| project_edit_batch | no tags | |
| project_delete_path | no tags | |
| project_create | no tags | |
| project_health | no tags | |
| project_cache_clear | no tags | |
| project_execute_js conditional | no tags | |
| project_trace_status | no tags | |
| project_read_audit | no tags | |
| project_shell_cancel_session | code-exec | code-exec: keyword "shell" in tool name |
| project_shell_run | code-exec | code-exec: keyword "shell" in tool name, parameter "command" |
| project_shell_status | code-exec | code-exec: keyword "shell" in tool name |
| project_shell_cancel | code-exec | code-exec: keyword "shell" in tool name |
| project_pr_create | no tags | |
| project_pr_comment | no tags | |
| project_pr_merge | no tags | |
| project_pr_list | no tags | |
| project_pr_close | no tags | |
| project_pr_reopen | no tags | |
| project_ci_status | no tags | |
| project_ci_control | no tags | |
| project_ci_trigger | no tags | |
| project_ci_logs | no tags | |
| project_ci_wait | no tags | |
| project_github_connect | no tags | |
| project_secret | no tags | |
| project_detect_harnesses | no tags | |
| project_install_self | no tags | |
| project_explain_error | no tags | |
| project_plan_read_batch | no tags | |
| project_snapshot | 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.
project_list_files → project_shell_cancel
A sensitive-source → external-sink chain exists: project_list_files → project_shell_cancel.
Supply chain and provenance
Integrityfirst-seen
Surface digeste40f634710326039
Scanned2026-11-09
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 1.19.0. Pin a release below and the command asks for exactly that one.
1.19.0
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 Venira 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.