mongodb-memory-mcp: Skill for Claude Code

.claude/skills/add-mcp-tool/SKILL.md

add-mcp-tool is a skill for Claude Code from jtv4k/mongodb-memory-mcp. It costs 77 tokens per session (2,882 once invoked), scanned A, original, Apache-2.0.

A guide for adding a new MCP tool, which lets an AI client call a server capability through a standard interface. It covers the input and output definitions, service method, registration, and tests.

In plain words
What is it for?
Use it to expose a new server action over MCP or safely change an existing tool’s input or output.
Why use it?
Adding only part of a tool can leave it unregistered, incorrectly validated, or separated from the application’s business logic.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md.

This is jtv4k/mongodb-memory-mcp's own configuration. It tells Claude Code how to work on mongodb-memory-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mongodb-memory-mcp configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is } from '../../domain/schemas.js';.

Reuse

Borrowing it

Nothing to install: this file belongs to jtv4k/mongodb-memory-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/jtv4k/mongodb-memory-mcp/main/.claude/skills/add-mcp-tool/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/jtv4k/mongodb-memory-mcp

Made for: Claude Code.

Wrote 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.

agentmods badge for add-mcp-tool

README.md
[![agentmods](https://agentmods.dev/badge/skills/jtv4k/mongodb-memory-mcp/add-mcp-tool/github.svg)](https://agentmods.dev/skills/jtv4k/mongodb-memory-mcp/add-mcp-tool)
Your own site
<a href="https://agentmods.dev/skills/jtv4k/mongodb-memory-mcp/add-mcp-tool"><img src="https://agentmods.dev/badge/skills/jtv4k/mongodb-memory-mcp/add-mcp-tool/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.

agentmods 80×15 button for add-mcp-tool

Your own site · 80×15
<a href="https://agentmods.dev/skills/jtv4k/mongodb-memory-mcp/add-mcp-tool"><img src="https://agentmods.dev/badge/skills/jtv4k/mongodb-memory-mcp/add-mcp-tool.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 77 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,882 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00077 $0.02882
Opus 5 $0.00039 $0.01441
Sonnet 5 $0.00015 $0.00576
Haiku 4.5 $0.00008 $0.00288

Measured 9d ago against content hash 2f5402b241c1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

add-mcp-tool scanned grade A with 0 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 9d 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/add-mcp-tool/SKILL.md · 287 lines

How it starts

The opening of the file, as written. The whole thing — 287 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Adding an MCP tool

A tool is five files, always in this order. Doing them out of order produces a tool the SDK will not register or, worse, one that skips cross-field validation.

Read src/mcp/tools/store-content.ts and src/mcp/tools/shared.ts first — they are the reference implementation, and everything below matches them.


Step 1 — Decide whether the service needs a new method

Transports hold no business logic (src/services/types.ts says so and means it). A tool validates input, calls exactly one KnowledgeService method, and formats the result.

If the capability does not already exist on KnowledgeService:

  1. Add the method to the KnowledgeService interface in src/services/types.ts, signature (input: XInput, ctx: RequestContext) => Promise<XResult>.
  2. Add XResult to src/domain/types.ts.
  3. Implement it inside createKnowledgeService() in src/services/knowledge-service.ts and add it to the returned object at the bottom of the factory.
  4. Wrap every MongoDB call in guarded(logger, 'collection.operation', () => …) so a raw MongoServerError never escapes as an unclassified failure.

If the capability is already on the service (listDocuments, getDocument, reembed, embeddingCoverage all exist and are currently only reachable over REST), skip to step 2.


Step 2 — Add the schemas to src/domain/schemas.ts

Three exports per tool, following the file's existing convention exactly:

// ---------------------------------------------------------------------------
// summarize_source
// ---------------------------------------------------------------------------

export const summarizeSourceShape = {
  sourceId: sourceIdSchema.describe('Source to summarise.'),
  maxChunks: z
    .number()
    .int()
    .min(1)
    .max(50)
    .default(10)
    .describe('How many leading chunks to include.'),
} satisfies z.ZodRawShape;

export const summarizeSourceSchema = z.object(summarizeSourceShape).superRefine(/* … */);
export type SummarizeSourceInput = z.infer<typeof summarizeSourceSchema>;

export const summarizeSourceOutputShape = {
  sourceId: z.string(),
  title: z.string(),
  chunkCount: z.number().int(),
  updatedAt: z.string(),
} satisfies z.ZodRawShape;

Read the full file on GitHub · 287 lines

Changes

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.

  1. 9d ago First seen · 287 lines · 77 tokens per session scan A 2f5402b241c1

Subscribe to this mod's changes

add-mcp-tool is a skill published in the GitHub repository jtv4k/mongodb-memory-mcp (0 stars, last pushed 3d ago), licensed Apache-2.0. It adds 77 tokens to every session and 2,882 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens