Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add build-with-dhiraj/ai-workflow-framework-portability-kit --skill add-custom-mcpgit clone --depth 1 https://github.com/build-with-dhiraj/ai-workflow-framework-portability-kitWrote 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/build-with-dhiraj/ai-workflow-framework-portability-kit/add-custom-mcp)<a href="https://agentmods.dev/skills/build-with-dhiraj/ai-workflow-framework-portability-kit/add-custom-mcp"><img src="https://agentmods.dev/badge/skills/build-with-dhiraj/ai-workflow-framework-portability-kit/add-custom-mcp/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/build-with-dhiraj/ai-workflow-framework-portability-kit/add-custom-mcp"><img src="https://agentmods.dev/badge/skills/build-with-dhiraj/ai-workflow-framework-portability-kit/add-custom-mcp.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 | $0.00086 | $0.01753 |
| Opus 5.5 | $0.00034 | $0.00701 |
| Sonnet 5.5 | $0.00017 | $0.00351 |
| Haiku 4.5 | $0.00009 | $0.00175 |
Grade D, and why
add-custom-mcp scanned grade D with 3 findings 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 25d 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.
Reaches for credential fileshighPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
2. **`~/.git-credentials`** — parse host-specific PAT (see [reference.md](reference.md) for the parser) Reads MCP configurationmediumAgent snooping
mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.
**Scope carries real consequences** — see [reference.md](reference.md) for the full comparison, but in short: `project` scope writes a `.mcp.json` meant to be committed to git, so secrets must never go there directly (us Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| npm downloads (30d) | 2× | `curl https://api.npmjs.org/downloads/point/last-month/<pkg>` | How it starts
The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add Custom MCP to Claude Code
End-to-end workflow: research → pick winner → configure auth → install → verify.
Claude Code manages MCP servers through the claude mcp CLI — never hand-edit
~/.claude.json or a project's .mcp.json directly; the CLI keeps scope and
JSON structure correct and merges idempotently on its own.
When to use
- User wants a new MCP server for any service
- User says "add MCP for X", "connect X to Claude Code", "find best X MCP"
- Replacing or upgrading an existing MCP entry
Execution checklist
Copy and track:
- [ ] 1. Scope — service name, read vs write, local/user/project config
- [ ] 2. Discover — GitHub + npm search, score candidates, pick winner
- [ ] 3. Auth — find existing local credentials; never invent secrets
- [ ] 4. Install — `claude mcp add` (idempotent by construction)
- [ ] 5. Verify — `claude mcp list`/`get`, ToolSearch, one live tool call
- [ ] 6. Report — winner repo, config location, verification result
Step 1 — Scope
Ask or infer:
| Question | Default |
|---|---|
| Which service? | From user message |
| Read-only or write? | Read-only unless user needs mutations |
| Config scope | local (this project only) unless user wants it everywhere (user) or shared with a team via git (project) |
Before adding: run claude mcp list — check if the server already exists under a similar key; claude mcp add on an existing name updates it, it won't duplicate.
Scope carries real consequences — see reference.md for the full comparison, but in short: project scope writes a .mcp.json meant to be committed to git, so secrets must never go there directly (use ${env:VAR} references instead).
Step 2 — Discover best GitHub repo
Run in parallel:
- GitHub search (
gh search repos "<service> mcp server" --sort=starsor WebSearch): sort by stars - Web search:
"<service> MCP server 2026" - npm search (if applicable):
npm search "<service> mcp"or checkhttps://api.npmjs.org/downloads/point/last-month/<pkg>
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 25d ago First seen · 174 lines · 86 tokens per session scan D 1726698b39a8
add-custom-mcp is a skill published in the GitHub repository build-with-dhiraj/ai-workflow-framework-portability-kit (5 stars, last pushed 12d ago), licensed MIT. It adds 86 tokens to every session and 1,753 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it D with 3 findings (reaches for credential files, reads mcp configuration, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-21.
Other skills, from other repositories
codeql
Run CodeQL database creation and security queries, add data-extension models, or process CodeQL SARIF. Use when CodeQL is explicitly requested; use security-review for a broader manual security review.
sharp-edges
Identify error-prone APIs, dangerous configuration, and footgun designs that enable security mistakes. Use for API ergonomics, misuse resistance, secure defaults, or pit-of-success reviews; use code-review for general defects.
code-quality
Agents should invoke this skill for code reviews, linting/formatting setup, maintainability checks, complexity concerns, warning cleanup, coding standards, or quality gates in Rust, TypeScript, Python, shell, and mixed repos.
code-reviewer
Review code for bugs, logic errors, security vulnerabilities, code quality issues, and adherence to project conventions, using confidence-based filtering to report only high-priority issues that truly matter. Use this skill when reviewing a small set of changes locally (such as unstaged diff), when dispatched as a…
differential-review
Performs security-focused differential review of code changes (PRs, commits, diffs). Adapts analysis depth to codebase size, uses git history for context, calculates blast radius, checks test coverage, and generates comprehensive markdown reports. Automatically detects and prevents security regressions.
huggingface-best
Find and compare recommended Hugging Face models for a task using benchmarks, model size, and device constraints. Use for model selection questions; use huggingface-local-models for GGUF setup and hf-cli for Hub operations.