Click on "Install 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., "@MCP LangChainJS Search Server search for RetrievalQA examples in langchainjs"
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.
Serveur MCP (Model Context Protocol) en TypeScript permettant de rechercher des exemples et du code dans le dépôt GitHub LangChainJS (langchain-ai/langchainjs). Il expose un outil search_langchain que les clients MCP (ex. Claude Desktop) peuvent appeler pour retrouver rapidement des snippets TS/JS/MD pertinents.
Outil principal: search_langchain
Source: GitHub Search Code API via @octokit/rest
Transport: stdio (pour intégration avec clients MCP)
Langage: TypeScript (build vers dist/)
Related MCP server: github-rag-mcp
Node.js 18+ et npm
(Optionnel) Un jeton GitHub personnel pour des quotas plus généreux
Variable d’environnement: GITHUB_TOKEN
npm install
npm run buildDéveloppement (TypeScript, sans build):
npm run devWatch (redémarrage auto):
npm run watchProduction (depuis dist/):
npm startLe serveur écoute via stdio et est destiné à être lancé par un client MCP.
Exemple de configuration Claude Desktop (à adapter à votre chemin local) :
{
"mcpServers": {
"langchain-js": {
"command": "node",
"args": [
"/chemin/vers/votre/projet/dist/index.js"
],
"env": {
"GITHUB_TOKEN": "votre_token_optionnel"
}
}
}
}Notes:
GITHUB_TOKEN est recommandé pour éviter les limitations strictes de l’API publique.
Ne commitez jamais de secrets. Préférez des variables d’environnement ou un fichier .env ignoré par Git.
Vous pouvez fournir un jeton GitHub pour augmenter les limites d’API :
export GITHUB_TOKEN=ghp_xxx_votre_tokenOu via un fichier .env (non commité) si votre outil de lancement le supporte.
search_langchain
Entrée:
query (string, requis): la requête de recherche (TS/JS/MD)
Sortie (texte): liste des correspondances avec nom, chemin, et URL HTML
Exemple d’appel (côté client MCP):
{
"name": "search_langchain",
"arguments": { "query": "RetrievalQA" }
}src/index.ts: serveur MCP + transport stdio, enregistrement des handlers
src/tools/search.ts: schéma de l’outil et handler search_langchain
src/github-client.ts: client GitHub (Octokit) pour recherche et lecture de contenu
src/types.ts: types internes (exemples, résultats)
npm run dev: exécute src/index.ts avec ts-node
npm run watch: redémarre avec nodemon sur changements
npm run build: compile TypeScript vers dist/
npm start: lance node dist/index.js
Erreurs 403/abuse/ratelimit: fournissez GITHUB_TOKEN.
Résultats vides: vérifiez la requête (query) et les extensions ciblées (TS/JS/MD).
Import/ESM: le projet est configuré en type: commonjs avec ts-node adapté; utilisez npm run build puis npm start en prod.
Ne mettez jamais un jeton en clair dans le dépôt.
Préférez des variables d’environnement et des gestionnaires de secrets.
ISC
Search for examples and code in the LangChainJS GitHub repository
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Search query for finding relevant examples (TS/JS/MD) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description must carry full behavioral disclosure. It only states the action and target, but does not disclose return value format, whether authentication is needed, any limits, or read-only nature. This is a minimal functional description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, front-loaded, no redundant information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Simple tool with one parameter and no output schema, but the description does not explain what result is returned or any usage caveats. For a search tool, knowing something about the return (list of files, code snippets) would be helpful, so it's adequate but not complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema covers 100% of parameters with a clear description ('Search query for finding relevant examples (TS/JS/MD)'). The tool description adds the context 'examples and code' but does not add additional parameter specifics, so baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Clear verb 'Search', specific resource 'LangChainJS GitHub repository', and object 'examples and code'. Though no siblings exist to differentiate from, the description is precise and unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives, no exclusions or context. Since there are no sibling tools, the absence is less critical, but the description still lacks any conditionality.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v1.0.0search_langchainWith only one tool available, there is no possibility of confusing it with another tool. The tool's purpose is clearly defined by its name and description.
The single tool name follows a clear verb_noun pattern (search_langchain), and since there are no other tools, there is no inconsistency to worry about.
The server is explicitly a search-only server, so one tool is arguably appropriate, but it falls below the typical 3-15 tool range, making it feel minimal.
For its stated purpose of searching LangChainJS examples and code, the tool provides the core functionality without obvious gaps. The agent can search and receive results directly.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Search GitHub, npm, PyPI, StackOverflow, ArXiv from one MCP — built for coding agents.
Code intelligence for coding agents: semantic, AST, graph, and full-text search. 279+ languages.
Code intelligence for LLMs. Analyze, search, and retrieve code from any public git repository.
Search @imqueue docs and scaffold typed services & clients from your AI coding agent.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/PlumyCat/mcp-github-langchain-js'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
