Postlyra remote MCP integration for Telegram creators — 0.2 release candidate
- ✓Actively maintained (<30d)
- ✓Clear description
- ✓Topics declared
- ✓Documented (README)
- !No standard license detected
git clone https://github.com/prof-1t/postlyra-mcp && cp postlyra-mcp/*.md ~/.claude/agents/Resumen de Subagents
# Postlyra MCP **Hosted MCP 0.3.5: post cards inside AI chats.** The endpoint exposes 32 tools. Desktop ChatGPT completed draft/card edits, browser source continuity, scheduling/moving/canceling, timed channel delivery and selected-message edit/delete with developer CSP enforcement enabled. The 804-test suite, typecheck/build and documentation checks passed. Group acceptance is blocked by a client safety review; remaining clients/devices are listed in [client evidence](docs/compatibility.md). See the [card guide](docs/chat-card.md). Registry version remains `0.2.0-rc.1`; OpenAI directory approval is not claimed. [Русский](README.ru.md) · [Website](https://postlyra.app/en) · [Connection guide](https://postlyra.app/en/connect) Save Telegram drafts, schedule publications and manage your content from an AI client. Postlyra is a hosted service. This repository contains public integration instructions, client configurations and diagnostics; it does not contain the private SaaS backend. No bot token or locally installed server is required. ## Connect - Remote MCP URL: **https://postlyra.app/mcp** - Transport: **Streamable HTTP** - Authentication: **OAuth with PKCE**, using your Postlyra account. 1. Open [Postlyra](https://postlyra.app/app) and sign in with Telegram. 2. Add your channel or group under Connections and grant @PostlyraBot the necessary rights. You may save drafts before connecting a destination. 3. Add the MCP URL in your AI client, follow its OAuth sign-in flow and review the requested permissions. 4. Ask the client to list your connected channels, then save a test draft. Configuration is complete only after authorization and a successful tool call. ### Claude Code ```text claude mcp add --transport http --scope user postlyra https://postlyra.app/mcp ``` Open `/mcp` and authenticate Postlyra. Alternatively merge [claude-code.json](clients/claude-code.json) into the project's `.mcp.json` without replacing other servers. This is a Claude Code configuration, not a Claude Desktop remote-connector configuration. [Official Claude Code instructions](https://code.claude.com/docs/en/mcp). ### Codex Merge [codex.toml](clients/codex.toml) into your Codex `config.toml`, preserving the existing configuration. Then run `codex mcp login postlyra` to start the separate MCP OAuth flow. [Official Codex instructions](https://learn.chatgpt.com/docs/extend/mcp?surface=cli). ### Cursor Merge [cursor.json](clients/cursor.json) into project `.cursor/mcp.json` or your global Cursor MCP configuration. Open the server settings and complete OAuth. [Official Cursor instructions](https://prod.cursor.com/docs/mcp). ### ChatGPT Enable Developer mode under **Settings → Security and login**, then open **Plugins**, select the plus button and add the public MCP URL. Review the discovered tools and complete Postlyra authorization. Account and workspace policy can affect availability. This describes a custom developer connection, not an approved catalog listing. [Official OpenAI instructions](https://developers.openai.com/plugins/deploy/connect-chatgpt). ### Claude Open **Customize → Connectors → Add custom connector**, enter the public MCP URL and select **Connect** to authorize Postlyra. Team/Enterprise owners may need to add the connector for their organization first. Claude's remote connection originates from Anthropic's infrastructure, including when using Claude Desktop; use the account connector interface rather than the local desktop-extension configuration. [Official Claude instructions](https://support.claude.com/en/articles/11175166-get-started-with-custom-connectors-using-remote-mcp). ## Example requests - “Save this text as a Postlyra draft titled Weekly recap.” - “Find my draft about the autumn launch and show it.” - “Find my music post and show its Postlyra card.” - “Schedule this post in my connected channel for September 22, 2026 at 10:00 Europe/Moscow.” - “Move that publication to September 23 at the same local time.” - “Apply the current version only to the publication in my news channel.” - “Cancel this scheduled publication.” - “Show posts that need attention.” Read [permissions](docs/permissions.md), [media transfer](docs/media.md), [troubleshooting](docs/troubleshooting.md) and the [compatibility record](docs/compatibility.md). ## Free Beta 5 channels/groups, 30 publications per day, 300 per 30-day period and 1 GB of media. For server-managed connected publications, one known target counts as one publication; technical retries are not additional publications. Native/inline flows use temporary holds and the confirmations available from Telegram, so exact recipient counting is not guaranteed. See [confirmation limits](docs/compatibility.md#telegram-confirmation-and-usage-limits). Publications include mandatory Postlyra attribution. AI-client subscriptions are separate. Drafts and publications are distinct. Saving content does not automatically edit sent messages. Native/inline Telegram shares may lack identifiers required for later message management; the original Postlyra draft remains editable. ## Diagnostics Node.js 18+: ```text node scripts/diagnose.mjs ``` This makes read-only checks of public metadata and unauthenticated MCP discovery. It does not authenticate, access drafts or publish anything. ## Distribution status [server.json](server.json) is published as [io.github.prof-1t/postlyra-mcp, version 0.2.0-rc.1](https://registry.modelcontextprotocol.io/v0.1/servers/io.github.prof-1t%2Fpostlyra-mcp/versions/0.2.0-rc.1). The official Registry API confirmed an active entry on September 11, 2026. The production endpoint also exposes the expanded tool metadata. Registry publication does not establish client compatibility or OpenAI catalog approval; no OpenAI submission is claimed. See the [release record](docs/release.md). ## Support [Postlyra support](https://t.me/postlyra) · [Privacy](https://postlyra.app/en/privacy) · [Terms](https://postlyra.app/en/terms) Never include access tokens, authorization codes, private previews or channel content in public issues. ## Official client references [Claude Code MCP](https://code.claude.com/docs/en/mcp) · [MCP remote registry](https://modelcontextprotocol.io/registry/remote-servers) · [Codex MCP](https://developers.openai.com/codex/mcp) · [Cursor MCP](https://docs.cursor.com/context/model-context-protocol)
Lo que la gente pregunta sobre postlyra-mcp
¿Qué es prof-1t/postlyra-mcp?
+
prof-1t/postlyra-mcp es subagents para el ecosistema de Claude AI. Postlyra remote MCP integration for Telegram creators — 0.2 release candidate Tiene 0 estrellas en GitHub y su última actualización registrada es del 2026-09-11.
¿Cómo se instala postlyra-mcp?
+
Puedes instalar postlyra-mcp clonando el repositorio (https://github.com/prof-1t/postlyra-mcp) o siguiendo las instrucciones del README en GitHub. ClaudeWave también te ofrece bloques de instalación rápida en esta misma página.
¿Es seguro usar prof-1t/postlyra-mcp?
+
Nuestro agente de seguridad ha analizado prof-1t/postlyra-mcp y le ha asignado un Trust Score de 70/100 (tier: OK). Revisa el desglose completo de comprobaciones superadas y flags en esta página.
¿Quién mantiene prof-1t/postlyra-mcp?
+
prof-1t/postlyra-mcp es mantenido por prof-1t. La última actividad registrada en GitHub es del 2026-09-11, con 0 issues abiertos.
¿Hay alternativas a postlyra-mcp?
+
Sí. En ClaudeWave puedes explorar subagents similares en /categories/agents, ordenados por popularidad o actividad reciente.
Despliega postlyra-mcp en tu cloud
Lleva este repo a producción en minutos. Cada plataforma genera su propio entorno con variables de entorno editables.
¿Mantienes este repo? Añade un badge a tu README
Pega el badge en tu README de GitHub para mostrar que está auditado por ClaudeWave. Cada badge enlaza de vuelta a esta página y muestra el Trust Score actual.
[](https://claudewave.com/repo/prof-1t-postlyra-mcp)<a href="https://claudewave.com/repo/prof-1t-postlyra-mcp"><img src="https://claudewave.com/api/badge/prof-1t-postlyra-mcp" alt="Featured on ClaudeWave: prof-1t/postlyra-mcp" width="320" height="64" /></a>Más Subagents
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
The agent that grows with you
Java 面试 & 后端通用面试指南,覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.
The agent engineering platform.
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.