Atlas / MCP servers / sparesparrow / Prompts Server

Prompts ServerBLOCK

mcp/sparesparrow/prompts-server

Model Context Protocol server for managing, storing, and providing prompts and prompt templates for LLM interactions.

Verdict
BLOCK
Grade
F
Trust score
46 /100
Exposed tools
109 92r · 15w · 2d
Transport
stdio
License
—
Stars
118
01

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

Simple MCP server for managing AI prompts and agent configurations with direct claude CLI orchestration.

What It Does

  • Stores prompts as JSON files in data/prompts/
  • Exposes MCP tools for querying and managing prompts
  • Provides agent templates for project orchestration
  • Works with Claude Desktop, Cursor, and other MCP clients

Quick Start

1. Install

pnpm install
pnpm build

2. Start MCP Server

pnpm start

3. Configure Claude Desktop

Add to ~/.claude/mcp.json:

{
"mcpServers": {
"prompts": {
"command": "node",
"args": ["/absolute/path/to/mcp-prompts/dist/mcp-server-standalone.js"],
"env": {
"PROMPTS_DIR": "/absolute/path/to/mcp-prompts/data/prompts"
}
}
}
}

4. Use in Claude

Ask Claude:

  • "List all prompts tagged with esp32"
  • "Get the esp32-fft-configuration-guide prompt"
  • "Create a new prompt for Python FastAPI best practices"

Orchestrating Projects

Use the orchestrate script to analyze entire projects:

./scripts/orchestrate-project.sh ~/projects/mia analyze
./scripts/orchestrate-project.sh ~/projects/esp32-bpm-detector review

This automatically:

  1. Detects project type
  2. Loads appropriate main agent
  3. Spawns specialized subagents
  4. Runs comprehensive analysis
  5. Returns structured results

MCP Tools

Prompts Organization

data/prompts/
├── main-agents/           # 7 project orchestration templates
│   ├── main_agent_python_backend.json
│   ├── main_agent_cpp_backend.json
│   ├
Read from source at commit 47a741a9e4fcOBSERVED · 2026-10-07
02

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.

claude-code
claude mcp add mcp-fbs --env STRIPE_SECRET_KEY=${STRIPE_SECRET_KEY} --env STRIPE_WEBHOOK_SECRET=${STRIPE_WEBHOOK_SECRET} -- npx -y @sparesparrow/[email protected]
claude-desktop
{
  "mcpServers": {
    "mcp-fbs": {
      "command": "npx",
      "args": [
        "-y",
        "@sparesparrow/[email protected]"
      ],
      "env": {
        "STRIPE_SECRET_KEY": "${STRIPE_SECRET_KEY}",
        "STRIPE_WEBHOOK_SECRET": "${STRIPE_WEBHOOK_SECRET}"
      }
    }
  }
}
03

Exposed tools (109)

92 read · 15 write · 2 destructive. Blast radius: 2 tools can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.

ToolRiskDescription
HighErrorRatereadHigh error rate in API Gateway
HighLatencyreadHigh latency in API Gateway
add_promptwrite
aggregate_embedded_telemetryreadAggregate telemetry data from multiple embedded devices
analyze_android_clipboard_patternsreadAnalyze clipboard usage patterns using cognitive prompts
analyze_changed_codereadAnalyze code changes using git diff + static analysis
analyze_codereadPerform unified static code analysis on source files
analyze_embedded_patternsreadAnalyze usage patterns across all embedded devices
analyze_telemetry_patternsreadAnalyze telemetry patterns using cognitive prompts
android-clipboard-analysis-workflowreadWorkflow for analyzing Android clipboard usage patterns
android_launch_appreadLaunch an app on Android device
android_play_soundreadPlay a sound on Android device
android_show_toastreadShow a toast message on Android device
android_take_screenshotreadTake a screenshot on Android device
apply_templatewrite
available_toolsreadDebugging tools available
backup_embedded_datareadBackup data from all embedded devices
build_configreadBuild system and configuration
calibrate_esp32_sensorsreadCalibrate ESP32 sensors
change_riskreadRisk of making changes during debugging
codereadCode to review
code_filesreadKey source files
configure_esp32writeSend configuration to ESP32 device
cpp-static-analysis-workflowreadSystematic workflow for C++ static analysis
cppcheck-config-desktop-general-defaultreadDefault cppcheck configuration for desktop C++ general analysis
cppcheck-config-embedded-esp32-memory-defaultreadDefault cppcheck configuration for ESP32 embedded memory analysis
cppcheck-config-embedded-esp32-security-defaultreadDefault cppcheck configuration for ESP32 embedded security analysis
create_promptwriteCreate a new prompt
database_typereadDatabase system type
debug_session_startwriteStart a debugging session with GDB/LLDB
delete_promptdestructive
detect-embedded-device-capabilitiesreadAnalyze embedded device capabilities and recommend appropriate tools
detect-embedded-project-contextreadAnalyze embedded project structure and requirements
detect-project-contextreadAnalyze project structure to determine type, language, and context
discover_embedded_devicesreadDiscover all available embedded devices (ESP32, Android)
docker_exec_analysiswriteExecute analysis tools in Docker containers
embedded-debugging-strategy-selectionreadMeta-cognitive strategy selection for embedded systems debugging
embedded-memory-constrained-analysisreadMemory analysis for resource-constrained embedded systems
embedded-system-quality-assessmentreadComprehensive quality assessment framework for embedded systems
embedded-systems-constraints-knowledgereadCore knowledge about embedded systems constraints and best practices
embedded-to-software-debugging-analogyreadApplying embedded systems debugging patterns to general software development
emergency_embedded_shutdownreadEmergency shutdown of all embedded devices
endpointreadAPI endpoint path
esp32-architecture-knowledgereadESP32 microcontroller architecture and constraints knowledge
esp32-debugging-workflowreadSystematic debugging workflow for ESP32 embedded systems
execute_cross_device_workflowwriteExecute a workflow that coordinates multiple embedded devices
filesreadList of key project files
get_android_battery_statusreadGet Android device battery status
get_android_clipboardreadGet current clipboard content from Android device
get_android_contextreadGet contextual information about Android device state
get_android_device_inforeadGet Android device information and capabilities
get_android_locationreadGet Android device location data
get_android_network_statusreadGet Android device network status
get_android_sensor_datareadGet Android device sensor data
get_embedded_contextreadGet contextual information about embedded device state
get_embedded_device_statusreadGet status overview of all embedded devices
get_esp32_statusreadGet current status and system information from ESP32
get_esp32_telemetryreadGet current telemetry data from ESP32 device
get_promptread
get_statsread
get_telemetry_historyreadGet historical telemetry data from ESP32
git_analyze_historywriteAnalyze git commit history for debugging insights
hardware_platformreadTarget hardware platform
hardware_specsreadTarget hardware specifications
identify-analysis-goalsreadDetermine the appropriate analysis goals based on project context and symptoms
interfacesreadCommunication interfaces used
languagereadProgramming language of the code
list_categoriesreadList all prompt categories with counts. Use this to discover categories before drilling into one with list_prompts.
list_promptsread
list_slash_commandsreadList available slash commands
memory-management-principlesreadCore principles of memory management across different programming paradigms
memory_constraintsreadMemory limitations
methodreadHTTP method
mock-workflowreadMock workflow for development
monitor_embedded_healthreadMonitor health and status of all embedded devices
parametersreadRequest parameters description
performance-regression-diagnosisreadSystematic approach to diagnosing performance regressions
performance_issuesreadKnown performance issues
predict_embedded_behaviorreadPredict device behavior based on historical patterns
problem_descriptionreadDescription of the debugging problem
project_contextreadProject type and characteristics
pylint-config-python-general-defaultreadDefault pylint configuration for Python general analysis
pylint-config-python-security-defaultreadDefault pylint configuration for Python security analysis
pytest-config-python-defaultreadDefault pytest configuration for Python test execution
queryreadSQL query to optimize
reset_esp32destructiveReset the ESP32 device
risk_levelreadCriticality of the project
root_contentsreadContents of root directory
rt_requirementsreadReal-time requirements
run_testswriteExecute tests with automatic framework detection
search_promptsreadSearch prompts by query
select-debugging-strategyreadChoose appropriate debugging strategy based on context and constraints
set_android_clipboardwriteSet clipboard content on Android device
slash_commandwriteExecute a slash command to quickly apply a prompt template
static-analysis-tools-knowledgereadKnowledge about static analysis tools and their capabilities
suggest_slash_commandsreadGet slash command suggestions based on a query
symptomsreadIssues or symptoms reported
sync_android_clipboardwriteSynchronize clipboard across devices
sync_clipboard_across_deviceswriteSynchronize clipboard content across all devices
system_access_levelreadLevel of system access (full, limited, remote)
table_sizereadApproximate table size
time_availablereadTime available for debugging
time_constraintreadAvailable time for analysis
two-phase-analysis-patternreadUniversal two-phase analysis pattern applicable across domains
update_promptwrite
use-git-integration-mcpreadDemonstrates using MCP tools for git-based development workflows
use-mcp-prompts-listreadDemonstrates how to use the list_prompts MCP tool
use-static-analysis-mcpreadDemonstrates using MCP tools for static analysis workflows
workflow_executewriteExecute a multi-tool orchestrated workflow
04

Trust audit

BLOCKgrade F · trust 46/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.

LayerWhat it checksResult
L0Provenance & inventoryWARN
L1Static analysis of the codeFAIL
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfaceWARN
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
declared (7 observation(s))
Network
declared (9 observation(s))
Shell
none-observed
Dependencies
not all pinned
Secrets in source
found

Findings (25)

HIGHFilesystem / path · fs.credential_store · CWE-22, CWE-59
scripts/deploy-docker.sh:327
- ~/.aws:/root/.aws:ro
Why it matters. touches a credential store
HIGHHard-coded secrets · secret.db_uri · CWE-798, CWE-321
.cursor/commands/deploy-mcp-json.md:16
"POSTGRES_URL": "postgres://postgres:postgres@localhost:5432/mcp_prompts",
HIGHHard-coded secrets · secret.db_uri · CWE-798, CWE-321
.cursor/environment.json:16
"POSTGRES_URL": "postgres://postgres:postgres@localhost:5432/mcp_prompts",
HIGHHard-coded secrets · secret.db_uri · CWE-798, CWE-321
archive/aws/Dockerfile.postgres:37
ENV POSTGRES_URL=postgres://postgres:postgres@postgres:5432/mcp_prompts
HIGHHard-coded secrets · secret.db_uri · CWE-798, CWE-321
docker-compose.postgres.yml:27
- POSTGRES_URL=postgres://postgres:postgres@postgres:5432/mcp_prompts
MEDIUMInventory / provenance · inv.binary · CWE-1104
data/learning.db
learning.db
Why it matters. a compiled or binary member cannot be reviewed from source
Fix. ship source, or explain the binary in the README
MEDIUMInventory / provenance · inv.binary · CWE-1104
dev-intelligence-orchestrator-v2.skill
dev-intelligence-orchestrator-v2.skill
Why it matters. a compiled or binary member cannot be reviewed from source
Fix. ship source, or explain the binary in the README
MEDIUMInventory / provenance · inv.binary · CWE-1104
dev-intelligence-orchestrator.skill
dev-intelligence-orchestrator.skill
Why it matters. a compiled or binary member cannot be reviewed from source
Fix. ship source, or explain the binary in the README
MEDIUMInventory / provenance · inv.binary · CWE-1104
scripts/__pycache__/parse_build_errors.cpython-312.pyc
parse_build_errors.cpython-312.pyc
Why it matters. a compiled or binary member cannot be reviewed from source
Fix. ship source, or explain the binary in the README
MEDIUMNetwork egress · net.raw_ip · CWE-200, CWE-319
src/core/services/automatic-prompt-generation.service.ts:59
fetch('http://127.0.0.1:7250/ingest/d33ee5cc-2ed5-4c57-a04d-227ffe7b5c8f',{method:'POST',headers:{'Content-Type':'application/json'},body:JSON.stringify({location:'automatic-prompt-generation.service.
MEDIUMNetwork egress · net.raw_ip · CWE-200, CWE-319
src/core/services/project-scaffold.service.ts:193
fetch('http://127.0.0.1:7250/ingest/d33ee5cc-2ed5-4c57-a04d-227ffe7b5c8f',{method:'POST',headers:{'Content-Type':'application/json'},body:JSON.stringify({location:'project-scaffold.service.ts:188',mes
MEDIUMHard-coded secrets · secret.db_uri · CWE-798, CWE-321
RELEASE_SUMMARY_v3.12.3.md:198
"POSTGRES_URL": "postgres://postgres:postgres@localhost:5432/mcp_prompts",
MEDIUMFilesystem / path · mcp.destructive_tools · CWE-22, CWE-59
delete_prompt, reset_esp32
Why it matters. 2 tool(s) can delete or overwrite
Fix. prefer a read-only mode or scoped tokens; the page states the blast radius
LOWInventory / provenance · inv.hidden_file · CWE-1104
.directory
.directory
Why it matters. hidden member outside the usual dotfiles
Fix. review its purpose
LOWInventory / provenance · inv.hidden_file · CWE-1104
.eslintignore
.eslintignore
Why it matters. hidden member outside the usual dotfiles
Fix. review its purpose
LOWInventory / provenance · inv.hidden_file · CWE-1104
.npmrc.github
.npmrc.github
Why it matters. hidden member outside the usual dotfiles
Fix. review its purpose
LOWInventory / provenance · inv.hidden_file · CWE-1104
.prettierignore
.prettierignore
Why it matters. hidden member outside the usual dotfiles
Fix. review its purpose
LOWInventory / provenance · inv.hidden_file · CWE-1104
.swcrc
.swcrc
Why it matters. hidden member outside the usual dotfiles
Fix. review its purpose
LOWInsecure crypto · crypto.weak_hash · CWE-327, CWE-338
AGENTS/prompts/hal-configuration-manager.json:5
"content": "# HAL Configuration Manager (ngapy-inspired)\n\nManage hierarchical configuration with intelligent caching for hardware abstraction layer.\n\n## Configuration Hierarchy\n\n```yaml\n# 1. Te
LOWInsecure crypto · crypto.weak_hash · CWE-327, CWE-338
packages/mcp-devtools-unified/src/services/knowledge-capture.service.ts:392
return require('crypto').createHash('md5').update(JSON.stringify(context)).digest('hex');
LOWFilesystem / path · fs.traversal · CWE-22, CWE-59
archive/aws/adapters/dynamodb-adapter.ts:3
import { IPromptRepository } from '../../core/ports/prompt-repository.interface';
LOWFilesystem / path · fs.traversal · CWE-22, CWE-59
archive/aws/adapters/dynamodb-adapter.ts:4
import { Prompt } from '../../core/entities/prompt.entity';
LOWFilesystem / path · fs.traversal · CWE-22, CWE-59
archive/aws/adapters/dynamodb-adapter.ts:5
import { PromptMetadata } from '../../core/entities/prompt-metadata.entity';
LOWFilesystem / path · fs.traversal · CWE-22, CWE-59
archive/aws/adapters/s3-adapter.ts:2
import { ICatalogRepository } from '../../core/ports/catalog-repository.interface';
LOWFilesystem / path · fs.traversal · CWE-22, CWE-59
archive/aws/adapters/sqs-adapter.ts:2
import { IEventBus } from '../../core/ports/event-bus.interface';

Gates applied: no_behavioural_pass.

Audited 2026-10-07 · audit v0.4.1 · source sha 47a741a9e4fcfull audit observations/trust-audit/mcp-server/sparesparrow__prompts-server.json · Report an issue / request a re-scan
05

Audit history

Every audit this server has had. A grade with a past is a grade somebody is still checking.

DateSourceVerdictGradeScoreChange
2026-10-0747a741a9e4fcBLOCKF46first audit
06

Questions

What is the Prompts Server MCP server?

Model Context Protocol server for managing, storing, and providing prompts and prompt templates for LLM interactions.

What tools does Prompts Server expose?

109 in total: 92 read-only, 15 that write, and 2 that can delete or overwrite (delete_prompt, reset_esp32). Every one is listed on this page with its risk.

Is Prompts Server safe to connect to an agent?

No — not without reading the findings first. The audit graded it F (46/100) and found 5 critical or high issues in the source. Each one is listed on this page with the file and line it is on. Separately from the audit: 2 of its tools can destroy data, so scope the token you give it to what you actually need.

What credentials does Prompts Server need?

It reads STRIPE_SECRET_KEY and STRIPE_WEBHOOK_SECRET from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.

How does Prompts Server run?

It speaks stdio, so it runs as a local process your client starts. It is published on npm as @sparesparrow/mcp-fbs at 1.0.0.

How current is this page?

The grade is for one exact copy of the source (47a741a9e4fc), read on 2026-10-07. The repository is watched and re-audited when it changes.

Advertisement