Capability 02 of 04 · Infrastructure
MCP & Tool Integration
How agents connect to external tools, APIs, and internal systems via MCP (now universal standard) and plugins.
5
maturity levels
15
practices
15
guides
L1 · Stage 01Ad-hoc
Practices - what it looks like3 guides
- Agent uses built-in tools onlyZero MCP is the baseline state: your AI agent has no programmatic connection to any tool, system, or data source outside its training data.guide→
- Agent relies on public / general knowledgeWhen an agent operates with only public API knowledge, it answers questions about your codebase using information from its training data - open-source documentation, public GitHubguide→
- Integrations done by copy-pasteCopy-paste integration is the universal first approach to giving AI agents context: a developer encounters a problem, grabs the relevant information (an error message, a stack tracguide→
Criteria - what to measure
- 01Agents use their built-in tools
- 02Agents draw on their general / built-in knowledge
- 03Team is aware of MCP as a standard for agent-tool integration
- 04Integrations, if any, are manual (copy-paste between tools)
L2 · Stage 02Guided
Practices - what it looks like3 guides
- 1-3 basic MCP servers (Git, Jira, docs)The first practical MCP deployment replaces the most expensive copy-paste operations with programmatic connections.guide→
- Manual MCP setup per developerManual MCP setup per developer is the phase where MCP servers exist and work, but each developer is responsible for installing and configuring them independently.guide→
- Basic tool authorization; mcp-auth-proxy for OAuth/token-persistence issuesBasic tool authorization is the first deliberate access control layer on MCP tool usage: decisions about which agents can call which tools, under what conditions.guide→
Criteria - what to measure
- 011-3 MCP servers are configured (e.g., Git, Jira, documentation)
- 02MCP setup is documented but configured manually per developer
- 03Basic tool authorization is implemented (agents authenticate to MCP servers)
- 04MCP server configurations are shared via repository (not local-only)
- 05At least one MCP server provides internal documentation or codebase context
L3 · Stage 03Systematic
Practices - what it looks like3 guides
- MCP platform: centralized server managementA centralized MCP platform moves server configuration, deployment, and credential management from individual developer machines to organization-managed infrastructure.guide→
- Architecture MCP, Ownership MCP, SLA MCP; deep-system MCPs (pentester-mcp, windbg-mcp, Pepper for iOS runtime)Specialized MCP servers organized by knowledge domain represent the L3 evolution from general-purpose data access to structured organizational intelligence.guide→
- RBAC per MCP tool; lazy tool-loading / MCP Tool Search (cuts token overhead and live attack surface; unloading unused servers recovers 24%+ context)Role-Based Access Control per MCP tool means defining precisely which agents can call which tools, based on the agent's role, the task it's performing, and the data it's operating on.guide→
Criteria - what to measure
- 01Centralized MCP platform manages server provisioning, configuration, and lifecycle
- 02Domain-specific MCP servers exist (Architecture MCP, Ownership MCP, SLA MCP)
- 03RBAC controls which agents can access which MCP tools
- 04MCP server health is monitored with alerting on downtime
- 05New MCP servers go through a standardized review and onboarding process
L4 · Stage 04OptimizedMost teams aim here
Practices - what it looks like3 guides
- Toolshed model: 400+ tools behind one MCP (Stripe)The Toolshed model, pioneered by Stripe, consolidates hundreds of distinct tools behind a single MCP endpoint.guide→
- Agent discovery: agent knows what tools are availableAgent discovery is the capability for an agent to dynamically enumerate what tools are available in its current environment and adapt its behavior accordingly.guide→
- MCP governance: lifecycle, versioning, provenance-checked installs (PolicyLayer State of MCP: 42% of 2,031 servers expose a destructive tool, 96.1% never warn the agent); defend against Agentjacking (malicious tool/error output treated as trusted remediation); per-MCP cost attribution via /usageMCP governance means treating MCP servers as production services with the same lifecycle management, change control, versioning, and audit requirements as any other production softguide→
Criteria - what to measure
- 01Toolshed model: 400+ tools accessible behind a unified MCP gateway (Stripe model)
- 02Agent discovery: agents can query available tools and their capabilities at runtime
- 03MCP governance covers lifecycle management, versioning, and audit logging
- 04MCP tool usage analytics track which tools are used, by which agents, how often
- 05MCP server versioning allows rollback to previous versions without downtime
L5 · Stage 05Autonomous
Practices - what it looks like3 guides
- MCP as nervous system: bidirectional context flowAt L5, MCP is no longer just a protocol for giving agents access to tools - it is the real-time information backbone that connects every part of the software delivery system.guide→
- Production → MCP → Agent → Code → Deploy → ProductionThe Production-MCP-Agent-Code-Deploy-Production loop is the fully autonomous software delivery cycle: production systems detect a condition (anomaly, performance degradation, configuide→
- Agent-to-Agent Protocol (A2A) + MCP combinedThe Agent-to-Agent Protocol (A2A), developed by Google and adopted as an open standard, defines how autonomous agents communicate with each other: how one agent delegates a task toguide→
Criteria - what to measure
- 01MCP operates as a bidirectional nervous system: production data flows to agents, agent actions flow to production
- 02Full production loop: Production -> MCP -> Agent -> Code -> Deploy -> Production
- 03Agent-to-Agent Protocol (A2A) and MCP are combined for multi-agent coordination
- 04MCP latency for context delivery is under 500ms P95
- 05A2A protocol enables agents to discover and delegate to other agents without human configuration
From the Field
Recent releases, projects and discussions the AI Radar classified into this capability.
release
@mcp-use/[email protected]
discovered
An evolutionary multi-agent collaboration platform based on AgentScope Java.
discovered
AI-powered travel hacking with points, miles, and award flights. Drop-in skills and MCP servers for OpenCode and Claude Code.
discovered
release
release
release
@upstash/[email protected]
release
Which level is your team at in MCP & Tool Integration?
The criteria above are what we check in a facilitated assessment. Run it yourself to place this capability, see which gates you have passed, and compare it against the other 3 in Infrastructure.
Start the assessment →