Server providing Argo CD integration for MCP clients.
Nothing to run from here
Spica 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
2
downloads a day
local
runs on your machine
256
downloads in 30d
What it does
MCP server for AI agents to interact with Spica servers — manage resources, databases, functions, storage, auditing, debugging and more.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user spica-mcp '--' npx -y @spica/mcp
# 2 — ask your agent for something these tools do
# list_apikeys, insert_apikey, update_apikey and 35 more
Spica costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
SPAll 1 server
@spica1 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 Spica 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 spica-mcp '--' npx -y @spica/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 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
38 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.
Returns all API keys from the Spica server. No pagination or filtering.
No parameter schema on file.
Creates a new API key. Use insert_policy to create a policy before associating it.
No parameter schema on file.
Updates an existing API key. _id is required. Use insert_policy to create or update a policy before associating it.
No parameter schema on file.
Returns identities with optional filtering and pagination.
No parameter schema on file.
Creates a new identity. Use insert_policy to create a policy before associating it.
No parameter schema on file.
Updates an existing identity. _id is required. Use insert_policy to create or update a policy before associating it.
No parameter schema on file.
Returns access policies with optional filtering and pagination.
No parameter schema on file.
Creates a new access policy.
No parameter schema on file.
Replaces an existing access policy. _id is required.
No parameter schema on file.
Returns users with optional pagination, sorting, and filtering.
No parameter schema on file.
Returns all bucket schemas from the Spica server.
No parameter schema on file.
Creates a new bucket schema. The 'properties' field defines the bucket's data model. Each property has a 'type' which can be: - Standard types: string, number, boolean, object, array - Spica types: relation (link to another bucket), storage (file reference), richtext, textarea, color, date,…
No parameter schema on file.
Replaces an existing bucket schema. _id is required. The 'properties' field defines the bucket's data model. Each property has a 'type' which can be: - Standard types: string, number, boolean, object, array - Spica types: relation (link to another bucket), storage (file reference), richtext,…
No parameter schema on file.
Returns documents from a bucket with optional filtering, pagination, sorting, and relation resolution.
No parameter schema on file.
Creates or updates a document in a bucket (upsert). When the document contains _id it is replaced, otherwise inserted. The document body must conform to the bucket's schema definition.
No parameter schema on file.
Fetches documents from a bucket and writes them to a local JSON or CSV file. Supports filter, limit, skip, sort. Efficient way for large dataset exports.
No parameter schema on file.
Reads a local JSON or CSV file and inserts its documents into a bucket in parallel batches. Use concurrency to control how many inserts run at once (default 50). Efficient way for large dataset imports.
No parameter schema on file.
Returns all serverless function objects.
No parameter schema on file.
Returns the source code (index) of a specific function.
No parameter schema on file.
Returns the installed dependencies and their versions for a specific function.
No parameter schema on file.
Returns all environment variable objects.
No parameter schema on file.
Creates a new environment variable.
No parameter schema on file.
Updates an existing environment variable. _id is required.
No parameter schema on file.
Returns all secret objects.
No parameter schema on file.
Creates a new secret.
No parameter schema on file.
Updates an existing secret. _id is required.
No parameter schema on file.
Creates a new serverless function. Use insert_env_var / insert_secret to create env vars and secrets before associating them.
No parameter schema on file.
Replaces an existing serverless function. _id is required. Use insert_env_var / insert_secret to create or update env vars and secrets before associating them.
No parameter schema on file.
Replaces and compiles the source code (index) of a function. Returns 204 on success or a compilation diagnostics error on failure.
No parameter schema on file.
Installs one or more npm packages as dependencies for a function.
No parameter schema on file.
Returns profiled entries for bucket data. Useful for debugging data distribution and patterns.
No parameter schema on file.
Returns profiled user entries. Useful for debugging user data patterns.
No parameter schema on file.
Returns function execution logs with optional filters for date range, function IDs, channel, log levels, and content search.
No parameter schema on file.
Returns activity / audit logs with optional filters for identifier, username, action type, resource, date range, and pagination.
No parameter schema on file.
Returns storage objects with optional filtering, pagination, and sorting.
No parameter schema on file.
Creates a new storage object. Content data must be base64-encoded.
No parameter schema on file.
Replaces an existing storage object. _id is required. Content data must be base64-encoded.
No parameter schema on file.
Renames a storage object by updating its metadata.
No parameter schema on file.
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under ISC
- 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 Spica 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 0.19.9 · scanned 15 Oct 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
Findings0 threat · 1 capability
Capabilityhigh
Coveragesource
Verificationsource
Surface digest71940a6ef2a5f371538cd601842da51beb787930706002ca27cbce4eb6f310ac
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 (38 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_apikeys | no tags | |
| insert_apikey | external-sink | external-sink: handler sends an HTTP POST ( client2.post("/passport/apikey") at dist/index.js:511, handler sends an HTTP PUT ( client2.put(/passport/apikey/${apikeyId}/policy/${pid}) at dist/index.js:515 |
| update_apikey | external-sink | external-sink: handler sends an HTTP PUT ( client2.put(/passport/apikey/${_id}) at dist/index.js:540, handler sends an HTTP PUT ( client2.put(/passport/apikey/${apikeyId}/policy/${pid}) at dist/index.js:546 |
| list_identities | no tags | |
| insert_identity | external-sink | external-sink: handler sends an HTTP POST ( client2.post("/passport/identity") at dist/index.js:608, handler sends an HTTP PUT ( client2.put(/passport/identity/${identityId}/policy/${pid}) at dist/index.js:615 |
| update_identity | external-sink | external-sink: handler sends an HTTP PUT ( client2.put(/passport/identity/${_id}) at dist/index.js:647, handler sends an HTTP PUT ( client2.put(/passport/identity/${identityId}/policy/${pid}) at dist/index.js:656 |
| list_policies | no tags | |
| insert_policy | external-sink | external-sink: handler sends an HTTP POST ( client2.post("/passport/policy") at dist/index.js:720 |
| update_policy | external-sink | external-sink: handler sends an HTTP PUT ( client2.put(/passport/policy/${_id}) at dist/index.js:739 |
| list_users | no tags | |
| list_buckets | no tags | |
| insert_bucket | external-sink | external-sink: handler sends an HTTP POST ( client2.post("/bucket") at dist/index.js:1002 |
| update_bucket | external-sink | external-sink: handler sends an HTTP PUT ( client2.put(/bucket/${_id}) at dist/index.js:1022 |
| list_bucket_data | no tags | |
| save_bucket_data | external-sink | external-sink: handler sends an HTTP PUT ( client2.put(/bucket/${bucketId}/data/${docId}) at dist/index.js:1100, handler sends an HTTP POST ( client2.post(/bucket/${bucketId}/data) at dist/index.js:1102 |
| export_bucket_data | state-write | state-write: declares readOnlyHint: false |
| import_bucket_data | external-sink | external-sink: handler sends an HTTP POST ( client2.post(/bucket/${bucketId}/data) at dist/index.js:1225 |
| list_functions | no tags | |
| get_function_index | no tags | |
| get_function_dependencies | no tags | |
| list_env_vars | no tags | |
| insert_env_var | external-sink | external-sink: handler sends an HTTP POST ( client2.post("/env-var") at dist/index.js:1422 |
| update_env_var | external-sink | external-sink: handler sends an HTTP PUT ( client2.put(/env-var/${_id}) at dist/index.js:1440 |
| list_secrets | sensitive-source | sensitive-source: keyword "list_secrets" |
| insert_secret | external-sink | external-sink: handler sends an HTTP POST ( client2.post("/secret") at dist/index.js:1483 |
| update_secret | external-sink | external-sink: handler sends an HTTP PUT ( client2.put(/secret/${_id}) at dist/index.js:1501 |
| insert_function | external-sink | external-sink: handler sends an HTTP POST ( client2.post("/function") at dist/index.js:1527, handler sends an HTTP PUT ( client2.put(/function/${fnId}/env-var/${eid}) at dist/index.js:1531, handler sends an HTTP PUT ( client2.put(/function/${fnId}/secret/${sid}) at dist/index.js:1536 |
| update_function | external-sink | external-sink: handler sends an HTTP PUT ( client2.put(/function/${_id}) at dist/index.js:1566, handler sends an HTTP PUT ( client2.put(/function/${fnId}/env-var/${eid}) at dist/index.js:1574, handler sends an HTTP PUT ( client2.put(/function/${fnId}/secret/${sid}) at dist/index.js:1589 |
| save_function_index | external-sink | external-sink: handler sends an HTTP POST ( client2.post(/function/${functionId}/index) at dist/index.js:1619 |
| save_function_dependencies | external-sink | external-sink: handler sends an HTTP POST ( client2.post(/function/${functionId}/dependencies) at dist/index.js:1645 |
| list_bucket_data_profile | no tags | |
| list_user_profile | no tags | |
| list_function_logs | no tags | |
| list_activities | no tags | |
| list_storage_objects | no tags | |
| insert_storage_object | external-sink | external-sink: handler sends an HTTP POST ( client2.post("/storage") at dist/index.js:1878 |
| update_storage_object | external-sink | external-sink: handler sends an HTTP PUT ( client2.put(/storage/${_id}) at dist/index.js:1896 |
| rename_storage_object | external-sink | external-sink: handler sends an HTTP PATCH ( client2.patch(/storage/${id}) at dist/index.js:1919 |
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.
list_secrets → import_bucket_data
A sensitive-source → external-sink chain exists: list_secrets → import_bucket_data.
Supply chain and provenance
Integrityfirst-seen
Surface digest71940a6ef2a5f371
Scanned2026-10-15
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 0.19.9. Pin a release below and the command asks for exactly that one.
0.19.9
30 Sep 2026
latestNo release note was published with this version.
0.18.37
undated
- The version this listing was on when mcprush began following its releases. The registry was not asked when it shipped, so this row carries no date.
—
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 Spica 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.