Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add latestaiagents/agent-skills/plugin install mcp-masteryWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/latestaiagents/agent-skills/mcp-client-integration)<a href="https://agentmods.dev/skills/latestaiagents/agent-skills/mcp-client-integration"><img src="https://agentmods.dev/badge/skills/latestaiagents/agent-skills/mcp-client-integration/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/latestaiagents/agent-skills/mcp-client-integration"><img src="https://agentmods.dev/badge/skills/latestaiagents/agent-skills/mcp-client-integration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00109 | $0.01509 |
| Opus 5.5 | $0.00044 | $0.00604 |
| Sonnet 5.5 | $0.00022 | $0.00302 |
| Haiku 4.5 | $0.00011 | $0.00151 |
Grade B, and why
mcp-client-integration scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads MCP configurationmediumAgent snooping
mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.
Claude Code reads this on startup. Add `.mcp.json` to `.gitignore` only if it contains secrets; otherwise commit it. How it starts
The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Client Integration
Wire any MCP server into the client that will consume it — declaratively for IDEs, programmatically for custom apps.
When to Use
- Installing an MCP server into Claude Desktop, Claude Code, or Cursor
- Building a custom MCP client (web app, CLI, agent framework)
- Debugging "server failed to start" or "no tools showing up"
- Sharing MCP config across a team
Config File Locations
| Client | Config path |
|---|---|
| Claude Desktop (macOS) | ~/Library/Application Support/Claude/claude_desktop_config.json |
| Claude Desktop (Windows) | %APPDATA%\Claude\claude_desktop_config.json |
| Claude Code | ~/.claude.json (user and local scope) or .mcp.json (project scope); add with claude mcp add |
| Cursor | ~/.cursor/mcp.json (user) or .cursor/mcp.json (project) |
Declarative Install — stdio Server
{
"mcpServers": {
"filesystem": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-filesystem", "/Users/me/projects"]
}
}
}
Declarative Install — Remote (Streamable HTTP) Server
{
"mcpServers": {
"linear": {
"type": "http",
"url": "https://mcp.linear.app/mcp"
}
}
}
Claude Code supports OAuth for remote servers: with no headers, authenticate from /mcp in a browser. For servers that take a static token, add "headers": { "Authorization": "Bearer ${TOKEN}" } (Claude Code expands ${VAR} and ${VAR:-default} in command, args, env, url, and headers). The legacy SSE transport ("type": "sse", often a /sse URL) is deprecated; prefer a server's Streamable HTTP endpoint.
Project-Scoped Config
Check a .mcp.json into the repo so teammates auto-inherit the right servers:
{
"mcpServers": {
"postgres-dev": {
"command": "npx",
"args": ["-y", "@bytebase/dbhub", "--dsn", "${DEV_DATABASE_URL:-postgresql://readonly@localhost:5432/dev}"]
}
}
}
Claude Code reads this on startup. Add .mcp.json to .gitignore only if it contains secrets; otherwise commit it.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago Changed · +3 lines scan C → B e32ffac844ab
- 2mo ago First seen · 146 lines · 109 tokens per session scan C 7f1c7a924ae2
mcp-client-integration is a skill published in the GitHub repository latestaiagents/agent-skills (6 stars, last pushed 2d ago), licensed MIT. It adds 109 tokens to every session and 1,509 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads mcp configuration). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
mcp-client-integration compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mcp-client-integrationlatestaiagents/agent-skills | Skill | 6 | 2d ago | MIT | B | 109 | Claude Code |
| nexent-daily-testModelEngine-Group/nexent | Skill | 6.1k | yesterday | MIT | A | 78 | Claude Code, Codex |
| ai-account-research-sales-cardskillsaiagent/aiskills | Skill | 5 | 5mo ago | none | A | 71 | Codex |
| ai-account-researchskillsaiagent/aiskills | Skill | 5 | 5mo ago | none | A | 65 | Codex |
| ai-amazon-brand-analyticsskillsaiagent/aiskills | Skill | 5 | 5mo ago | none | A | 72 | Codex |
| ai-amazon-international-listingsskillsaiagent/aiskills | Skill | 5 | 5mo ago | none | A | 75 | Codex |
| ai-amazon-repricing-strategyskillsaiagent/aiskills | Skill | 5 | 5mo ago | none | A | 75 | Codex |