MCP server for the @agentutility web-probe cluster — pay-per-call x402 tools, no API keys, USDC on Base.
from $12/mo
Nothing to run from here
Sprigr 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.
Open Installation—
p95 latency
—
call success
local
runs on your machine
—
calls last 7d
What it does
Sprigr MCP server — local AI agent search with WASM-powered full-text search and hybrid semantic search. Also exports a Workers-compatible runtime for in-process search inside Cloudflare Workers / bundled environments.
Quickstart
# 1 — run it from where its publisher ships it
npx -y @sprigr/mcp-server
# 2 — ask your agent something
> Sprigr MCP server — local AI agent search with WASM-powered full-text search and hybrid semantic search. Also exports a Workers-compatible
Sprigr is free: there is no plan to choose, no cap to set and nothing that can bill you.
Publishernot claimed
SPAll 1 server
@sprigr1 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 Sprigr 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. It is scanned, signed and pinned to the version you choose — 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. Claude Code registers it in one command.
claude mcp add sprigr-mcp -- npx -y @sprigr/mcp-serverReconnect, or start a new session, and the tools appear in the model’s tool list.
Free to install, and it runs from its publisher’s own package: no account, no key, no card.
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
20 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.
Get instructions for creating a Sprigr account and API key.
Takes no parameters.
Example callreturns →
List all search indexes in your Sprigr account. Shows index names, object counts, descriptions, and when they were last updated.
Takes no parameters.
Example callreturns →
Create a new search index and configure its settings.
Takes no parameters.
Example callreturns →
Update settings for an existing search index. Change searchable attributes, faceting, ranking, or synonyms.
Takes no parameters.
Example callreturns →
Import (upsert) JSON objects into a search index. Each object must have a unique objectID.
Takes no parameters.
Example callreturns →
Dedup-aware insert for AI-AGENT MEMORY. Before storing a fact, it checks the
Takes no parameters.
Example callreturns →
Search an index with full-text search, optionally with semantic (vector) search.
Takes no parameters.
Example callreturns →
Get statistics for your Sprigr account: index count, total objects, storage used.
Takes no parameters.
Example callreturns →
Delete objects from an index by their objectIDs. Maximum 1000 IDs per call.
Takes no parameters.
Example callreturns →
Fetch a single object from an index by its objectID. Useful for retrieving a specific record without searching.
Takes no parameters.
Example callreturns →
Permanently delete an entire index, including all its objects, facet data, and settings. This action cannot be undone.
Takes no parameters.
Example callreturns →
Remove all objects from an index but keep the index settings (searchable attributes, facets, etc.).
Takes no parameters.
Example callreturns →
Export (download) all objects from an index as JSON. Supports pagination for large indexes.
Takes no parameters.
Example callreturns →
Search across multiple indexes in a single call. Returns results from each index tagged with their source.
Takes no parameters.
Example callreturns →
Point an alias name at a real index. After setting, you can use the alias name anywhere you would use an index name
Takes no parameters.
Example callreturns →
Remove an index alias. After deleting, the alias name will no longer resolve to any index.
Takes no parameters.
Example callreturns →
List all index aliases in your account. Shows which alias points to which real index.
Takes no parameters.
Example callreturns →
Create a new API key for your Sprigr account. Use this to create restricted keys for
Takes no parameters.
Example callreturns →
Mint a SECURED (scoped) API key from your SEARCH key. A secured key carries a
Takes no parameters.
Example callreturns →
List all API keys in your account with their types and index restrictions.
Takes no parameters.
Example callreturns →
Freeyour plan
$0 forever
- Every tool, no call limit
- No card, no account needed
- Source published under a licence you can read
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because nothing bills
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable. Sprigr costs nothing to install and nothing to call, 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: $8.42
$16.58 left
ATrust score 95 / 100
Release 1.17.0 · scanned 25 Aug 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 score95
Findings1 threat · 0 capability
Capabilitymoderate
Coveragesource
Verificationnone
Surface digestea15caec0c82dd337799b0f946f2e55c8352ff9950ec7655e65b07e2d48d158c
Score vectorthreat 100 → client 95
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| verification-discount | none | publisher verification (unlinked) — no provenance/repo link, but the shipped source was fully read | −2 |
| 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 (20 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 |
|---|---|---|
| signup | no tags | |
| list_indexes | no tags | |
| create_index | no tags | |
| update_settings | no tags | |
| import_objects | no tags | |
| smart_import | no tags | |
| search | no tags | |
| get_stats | no tags | |
| delete_objects | no tags | |
| get_object | untrusted-input | |
| delete_index | no tags | |
| clear_index | no tags | |
| export_objects | no tags | |
| multi_search | no tags | |
| set_alias | no tags | |
| delete_alias | no tags | |
| list_aliases | no tags | |
| create_api_key | no tags | |
| create_secured_key | no tags | |
| list_api_keys | 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 digestea15caec0c82dd33
Scanned2026-08-25
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
Pinned to 1.17.0 — the install command below asks for that release. A pin is part of an install, so it is kept for this visit and written down when you install.
1.17.0
undated
installedNo release note was published with this version.
—
no reviews yet
Reviews are earned
Only accounts with at least 50 real tool calls against this server in the last 90 days can post. Ratings are weighted by how much the reviewer actually uses it, and publishers can reply once per review.
Reviews are earned
Writing one takes an account with at least 50 real tool calls against Sprigr in the last 90 days. That is the whole gate — there is no other way to post, which is why the counts beside each review are worth reading.
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 an account with 50 real tool calls against it.