Developer Tools
jamesross.ai
Provides tools for searching architecture patterns, evaluating agent workspaces, pricing context, and checking redaction for AI agent development.
ENDPOINT 1
https://jamesross.ai/mcp
MCP server metadata
- Name
- jamesross-practice
- Version
- 1.1.0
James Ross runs an agent-ready knowledge architecture practice: making an organisation's knowledge legible to AI agents, so an agent can work on it without a human re-explaining the business every session. These six tools expose the practice's own instruments. Full-text search across the published architecture writing (search_architecture), covering the patterns, the evaluation method, the learn track and the teardowns. The 18-pattern architecture library (lookup_pattern). The workspace-maturity and organisational-readiness assessments (assess_workspace). The context-position cost model (price_context_read), and the redaction pre-flight scanner (check_redaction). If you needed a capability that isn't here, say so with request_capability. The same searchable corpus is also published as resources under the architecture:// scheme, so resources/list and resources/read give you the section text directly. Calls are logged anonymously: the tool name, a timestamp, and a minimal derived summary of the arguments, kept so the practice can see which capabilities agents actually reach for. There is no account, no identifier and no session. check_redaction is the strict case. It logs finding counts only, never the text you scanned and never what matched. Send no secrets or personal data to any tool here.
Known tools 6
search_architectureFull-text search across the published architecture corpus: the 18 patterns and how they compose, the evaluation method, the seven learn-track modules, and the teardowns of other people's published agent systems.
Inferred read-onlylookup_patternSearch the 18 architecture patterns behind this practice by keyword or by pattern number.
Inferred read-onlyassess_workspaceScore an agent workspace across six dimensions: canonical knowledge, memory and context economics, verification and oversight, safety and permissions, telemetry and cost, provenance and delegation.
Inferred read-onlycheck_redactionScan text for the shapes of private content before it goes anywhere public: email addresses, absolute home paths, credential and token prefixes, private and link-local IPs, .
Potential side effectsrequest_capabilityTell this server what capability you needed but didn't find here.
Inferred read-onlyCONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.jamesross-practice]
url = "https://jamesross.ai/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"jamesross-practice": {
"type": "http",
"url": "https://jamesross.ai/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: jamesross-practice
Remote MCP URL: https://jamesross.ai/mcp
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"jamesross-practice": {
"url": "https://jamesross.ai/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"jamesross-practice": {
"type": "http",
"url": "https://jamesross.ai/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "jamesross-practice",
"transport": "streamable-http",
"url": "https://jamesross.ai/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Loading Trust v2 evidence…
Checking the associated registrable domain. The BuiltWith key remains server-side.
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.