Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Agent Context MCP show me the latest context revisions for the sales-agent pod"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Provider-neutral MCP binding for the Agent Context Charter.
This repository defines how an Agent Context Graph and ContextPod contract are
exposed through MCP. It does not ship GCP, Pinecone, Cloudflare, database, or
hosted Pod connectors. A provider implements the ContextPodProvider contract
and supplies its own storage, API, deployment, and durable event log.
Resources:
context://graph
context://pods/{pod_id}Tools:
context_describe
context_resolve
context_revisions
context_events
context_event_appendcontext_event_append applies the Charter's required semantic pipeline steps
(redaction, cache invalidation, supersession, conflict escalation, and release
eligibility) without guessing provider-specific side effects. The adapter
replays accepted Pod events before resolving so the semantic state survives a
process restart.
Related MCP server: Klarova
npm install
npm testCheck a Provider's remote MCP server without invoking any mutating tool:
AGENT_CONTEXT_MCP_BEARER_TOKEN=... npm run conformance -- https://provider.example.com/mcpThe normative graph document is docs/AGENT_CONTEXT_GRAPH.md.
The MCP binding and conformance rules are docs/MCP_PROFILE.md.
The YAML fixture is docs/sales-agent.graph.yaml.
The machine-readable graph schema is spec/agent-context-graph.schema.json.
This server cannot be deployed
Guarded MCP server for agent-readable business truth, provenance, readiness, and discovery.
Hosted MCP memory and agent control plane for durable conversations, jobs, and operations.
MCP-first control plane for ProAgentStore agents and private instances.
The Cortex MCP server provides read-only access to real-time engineering context from the Cortex developer portal, allowing AI coding assistants to answer natural language questions about your organization's catalog (microservices, libraries, domains, teams, infrastructure), scorecards (engineering standards and best practices), initiatives (goals and deadlines), and Engineering Intelligence metrics. It includes tools for querying documentation, tracking personal entities, and accessing AI-assisted insights across the entire Cortex ecosystem.
