Sprout MCP
PYPI · SPROUT-MCP · SCANNED SEP 20
Model-tiered content pipeline — cheap models seed, expensive models verify
Available components
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security100
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- Runs hatchling.build at install time, a recognised native-build step with no shell scripting around it. View diagnostics → Pass
- 1 of 16 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency32
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- License check failed: the license (MIT License) isn't a recognized OSI-approved license. See how to fix → Fail
- Actively maintained (last published 206 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability69
- AI-judged instruction clarity (good).Pass
- Tool/resource definitions use about 820 tokens (~63/item across 13 items; 13 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management83
- Stability observed for 25 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
- Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 13 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 14 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a current MCP spec version (2026-07-28).Pass
How do I install the Sprout MCP server?
Sprout MCP runs locally as a PyPI package, launched with uvx sprout-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
pypi · sprout-mcp
claude mcp add mepsopti-sprout-mcp -- uvx sprout-mcp
{
"mcpServers": {
"mepsopti-sprout-mcp": {
"command": "uvx",
"args": [
"sprout-mcp"
]
}
}
} {
"servers": {
"mepsopti-sprout-mcp": {
"command": "uvx",
"args": [
"sprout-mcp"
]
}
}
} codex mcp add mepsopti-sprout-mcp -- uvx sprout-mcp
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"mepsopti-sprout-mcp": {
"type": "local",
"command": [
"uvx",
"sprout-mcp"
],
"enabled": true
}
}
} openclaw mcp add mepsopti-sprout-mcp --command uvx --arg sprout-mcp
mcp_servers:
mepsopti-sprout-mcp:
command: "uvx"
args: ["sprout-mcp"] {
"McpServers": {
"mepsopti-sprout-mcp": {
"Transport": "stdio",
"Command": "uvx",
"Arguments": [
"sprout-mcp"
]
}
}
} assistant mcp add mepsopti-sprout-mcp -t stdio -c uvx -a sprout-mcp
{
"mcpServers": {
"mepsopti-sprout-mcp": {
"command": "uvx",
"args": [
"sprout-mcp"
]
}
}
} Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 19 Sept 26 −3
- Stability: pass → 0.80 functional
- 18 Sept 26 +16
- Malware scan: unverified → pass ▲ security
- Stability: 0.97 → pass security
- 17 Sept 26 −15
- Malware scan: pass → unverified ▼ security
- 16 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.
- 15 Sept 26 +15
- Malware scan: unverified → pass ▲ security
- 14 Sept 26 −14
- Malware scan: pass → unverified ▼ security
- 12 Sept 26 +12
- Malware scan: unverified → pass ▲ security
- Stability: pass → 0.80 functional
- 11 Sept 26 −14
- Malware scan: pass → unverified ▼ security
- Stability: 0.97 → pass security
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 20 Sept 2026 · Analysed pypi/sprout-mcp@0.1.4
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | pypi |
Background: How many MCP packages publish verified provenance →
Install scripts 1 script
| Hook | Tier | Command |
|---|---|---|
| build_backend | allowlisted | hatchling.build |
Background: Why install scripts are a supply-chain risk →
Dependencies 16 packages
| Packages resolved | 16 |
|---|---|
| Stale | 1 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
cancel_scheduled Cancel Scheduled ~30
Cancel a pending scheduled task.
| Name | Type | Req | Description |
|---|---|---|---|
| task_id | string | yes | Full or partial UUID of the task |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
configure_routing Configure Routing ~73
Add or update a routing rule for a task type.
| Name | Type | Req | Description |
|---|---|---|---|
| reason | string | yes | Why this tier is appropriate |
| task_type | string | yes | Task type name (e.g. "code_review", "summarization") |
| tier | string | yes | Model tier — haiku, sonnet, or opus |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
export_chunks Export Chunks ~51
Export verified chunks as JSON compatible with enrich-nodes.js.
| Name | Type | Req | Description |
|---|---|---|---|
| min_confidence | string | – | Minimum confidence level (seed, watered, sprouted). Default: watered |
| project | – | – | Optional project filter |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
get_cost_report Get Cost Report ~26
Get estimated cost report by model and project.
| Name | Type | Req | Description |
|---|---|---|---|
| project | – | – | Optional project filter |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
get_review_queue Get Review Queue ~58
List chunks needing review.
| Name | Type | Req | Description |
|---|---|---|---|
| confidence | – | – | Filter by confidence level (seed, watered) |
| limit | integer | – | Max results (default 50) |
| node_type | – | – | Filter by node type |
| project | – | – | Filter by project |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
get_stats Get Stats ~28
Get dashboard of chunk counts by confidence level and token usage.
| Name | Type | Req | Description |
|---|---|---|---|
| project | – | – | Optional project filter |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
list_scheduled List Scheduled ~14
View pending scheduled tasks.
Input schema present but exposes no named parameters.
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
mark_reviewed Mark Reviewed ~92
Promote or reject a chunk after review.
| Name | Type | Req | Description |
|---|---|---|---|
| chunk_id | string | yes | UUID of the chunk |
| new_confidence | string | yes | New confidence level (watered, sprouted, rejected) |
| review_notes | – | – | Optional rejection reason or reviewer comments |
| verified_by | string | yes | Model or person that reviewed (e.g. "sonnet-4.6", "opus-4.6") |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
opus_test Opus Test ~44
Generate structured review summary for the OpusTest workflow. Groups all seed/watered chunks by type with source URLs, ready for Sonnet first-pass then Opus final-pass.
Input schema present but exposes no named parameters.
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
recommend_model Recommend Model ~42
Get model recommendation for a task type.
| Name | Type | Req | Description |
|---|---|---|---|
| task_type | string | yes | The type of task (e.g. "biography_synthesis", "fact_check_final") |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
retry_on_error Retry On Error ~79
Record a failed attempt for a chunk and get retry guidance. Call this when a model call fails (e.g. 500 error). Sprout tracks retry count and tells you whether to retry or escalate.
| Name | Type | Req | Description |
|---|---|---|---|
| chunk_id | string | yes | The chunk ID that failed |
| error_message | string | yes | The error message from the failed attempt |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
schedule_task Schedule Task ~97
Schedule a task to run at a specific time or after a delay.
| Name | Type | Req | Description |
|---|---|---|---|
| delay_minutes | – | – | Minutes from now to run |
| run_at | – | – | ISO datetime for when to run (e.g. "2026-02-26T02:00:00-07:00") |
| task_name | string | yes | Task to run (opus_test, export_chunks, get_stats) |
| task_params | – | – | Optional JSON string of parameters |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
submit_chunk Submit Chunk ~168
Store content with provenance tracking.
| Name | Type | Req | Description |
|---|---|---|---|
| content | string | yes | The actual content |
| field | string | yes | Field name (e.g. "biography", "description") |
| node_id | string | yes | Node identifier (e.g. "cath-person-001") |
| node_type | string | yes | Node type (e.g. "Person", "Council", "Document") |
| produced_by | string | yes | Model that produced it (e.g. "haiku-4.5", "sonnet-4.6", "opus-4.6") |
| project | string | yes | Project name (e.g. "theology") |
| sources | – | – | URLs used as sources |
| task_type | string | yes | Type of task (e.g. "biography_synthesis") |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
What is the Sprout MCP server?
Sprout MCP is listed in the public MCP registry as io.github.mepsopti/sprout-mcp. Model-tiered content pipeline, cheap models seed, expensive models verify. This page covers its PyPI package (sprout-mcp).
Is the Sprout MCP server safe to use?
Sprout MCP scores 78 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the Sprout MCP server expose?
Sprout MCP exposes 13 tools: submit_chunk, get_review_queue, mark_reviewed, recommend_model, get_stats, and 8 more. Their descriptions and schemas cost roughly 802 tokens of context every time the server is loaded.
Is the Sprout MCP server still maintained?
Sprout MCP is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.