Mcp Probe Kit
A comprehensive development toolkit that actually tries to teach AI agents about your codebase structure. It bundles 27 tools across the full cycle: product specs, UI design syncing, Git commits, code reviews, test generation, and bug workflows that default to Toyota's TBP 8-step root cause analysis before patching. The code graph bridge talks to GitNexus for impact analysis during feature starts and bugfixes. Memory tools run on Qdrant with Ollama or OpenAI-compatible embeddings to store reusable patterns across repos. It also reads local Cursor conversation history directly from the SQLite database. You'd reach for this if you want orchestrated workflows instead of single-shot commands, or if you're tired of AI forgetting project context between sessions.
- GitHub stars
- 41
- tools
- 31
- transport
- STDIO
- last updated
- Aug 11, 2026
Tools
31 toolsPublic tool metadata for what this MCP can expose to an agent.
workflowFallback tool-selection guide for choosing the appropriate workflow.
Fallback tool-selection guide for choosing the appropriate workflow.
No parameter schema in public metadata yet.
plan_heartbeat
No parameter schema in public metadata yet.
resume_plan
No parameter schema in public metadata yet.
converge
No parameter schema in public metadata yet.
start_feature
No parameter schema in public metadata yet.
start_bugfix
No parameter schema in public metadata yet.
start_onboard
No parameter schema in public metadata yet.
start_ui
No parameter schema in public metadata yet.
start_product
No parameter schema in public metadata yet.
start_ralph
No parameter schema in public metadata yet.
init_project
No parameter schema in public metadata yet.
init_project_context
No parameter schema in public metadata yet.
check_spec
No parameter schema in public metadata yet.
estimate
No parameter schema in public metadata yet.
architecture
No parameter schema in public metadata yet.
code_insight
No parameter schema in public metadata yet.
gentest
No parameter schema in public metadata yet.
code_review
No parameter schema in public metadata yet.
refactor
No parameter schema in public metadata yet.
gencommit
No parameter schema in public metadata yet.
git_work_report
No parameter schema in public metadata yet.
ui_design_system
No parameter schema in public metadata yet.
ui_search
No parameter schema in public metadata yet.
interview
No parameter schema in public metadata yet.
history_session_bootstrap
No parameter schema in public metadata yet.
search_memory
No parameter schema in public metadata yet.
read_memory_asset
No parameter schema in public metadata yet.
memorize_asset
No parameter schema in public metadata yet.
update_memory_asset
No parameter schema in public metadata yet.
delete_memory_asset
No parameter schema in public metadata yet.
scan_and_extract_patterns
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageReadme
mcp-probe-kit — Know the Context, Feed the Moment
知时MCP | mcp-probe-kit
Know the Context, Feed the Moment.
Introspection · Context Hydration · Delegated Orchestration
Talk is cheap, show me the Context.
mcp-probe-kit is a protocol-level toolkit designed for developers who want AI to understand project intent, choose a precise workflow, and retain validated experience without flooding the model with internal actions.
Languages: English | 简体中文 | 日本語 | 한국어 | Español | Français | Deutsch | Português (BR)
Details
- Repository
- github.com/mybolide/mcp-probe-kit
- Categories
- AI & LLM Tools, Automation & Workflows
- Package
mcp-probe-kit- Transport
- STDIO
- Registry
- MCP registry, active
Related AI & LLM Tools MCP servers
View all
bhivedartkeyai/bhived-mcpShared memory for AI agents: query proven fixes, avoid known mistakes, and find skills and MCPs.35stars
Enquire Mcpoomkapwn/enquire-mcpLong-term memory for AI agents — your Obsidian vault as searchable persistent memory.34stars
Selvageselvage-lab/selvageAn LLM-based code review MCP server with AST-powered smart context extraction33stars
Workflows Mcp Servercyanheads/workflows-mcp-serverStore, query, and create YAML workflow playbooks for LLM agents.32stars
ThumbGate — PreToolUse Agent Firewalligorganapolsky/thumbgateSub-ms PreToolUse firewall, feedback memory, and single-use permits for AI coding agents.31stars