Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Dev Context Connector

    1

    Connects your agent to Context Bridge, a local MCP server for Jira, Sentry, and GitHub Actions. One endpoint, three tools, no hosted infrastructure.

    Free

    Security scanned
    Dev Context Connector

    Dev Context Connector

    Example session with this skill installed

    Find the latest errors in the 'web-frontend' Sentry project and check if there is a Jira ticket for the top one.

    • Read your context and instructions
    • Compiled the dev context connector
    • Generated the document

    I have queried Sentry for the latest unresolved issues in the `web-frontend` project and checked Jira for related records. ## Production Issue Report | Source | ID / Key | Title / Summary | Status | Details | | :--- | :--- | :--- | :--- | :--- | | **Sentry** | `E-9921` | `TypeError: null is not an object (evaluating 'e.profile')` | Unresolved | 4.2k events, Culprit: `UserDashboard.tsx` | | **Jira** | `PROJ-442` | `Frontend: Fix TypeError in UserDashboard profile lookup` | IN PROGRESS | Assignee: @jdoe, Created: 2 days ago | | **Sentry** | `E-9918` | `ChunkLoadError: Loading chunk 404 failed` | Unresolved | 128 events, Culprit: `webpack/runtime` | | **Jira** | `N/A` | No matching ticket found | N/A | Recommend creating a new issue for this error | **System Health Summary** The primary error (`E-9921`) is already being tracked in Jira as `PROJ-442` and is currently in progress. The secondary error regarding `ChunkLoadError` appears to be a new regression with no corresponding Jira ticket yet. **Next steps** 1. Review the assignee's progress on `PROJ-442` in Jira. 2. Check GitHub Actions for the `main` branch to see if recent deployments introduced the `ChunkLoadError`. 3. Create a Jira ticket for the `ChunkLoadError` if it persists after the next deploy.

    UserDashboard.tsx

    PDF · document

    Generated

    Example file from a real run - the skill writes it into your workspace.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Your agent can't help with a ticket, a production error, or a failing build if it can't see any of them. Dev Context Connector wires your agent into Context Bridge — a local MCP server that puts Jira, Sentry, and GitHub Actions behind one endpoint. Once connected, the agent can fetch a ticket, list unresolved Sentry issues, or check CI status without you tab-switching. WHAT YOU GET - SKILL.md — the skill definition and when-to-use rules - reference/setup.md — the exact MCP config for Claude Code, Cursor, and any stdio client, plus how to create the API tokens WHAT IT CONNECTS TO - Context Bridge MCP server (pip install context-bridge-mcp) - Jira (via JIRA_BASE_URL, JIRA_EMAIL, JIRA_API_TOKEN) - Sentry (via SENTRY_ORG_SLUG, SENTRY_AUTH_TOKEN) - GitHub Actions (via GITHUB_PERSONAL_ACCESS_TOKEN) WHAT IT DOES NOT DO - No hosted infrastructure. The server runs on your machine. - No write actions. Context Bridge is read-only. - No data leaves your machine beyond the API calls the server itself makes. Built by the author of ghost-tracer, ghost-reason, and context-bridge-mcp (Official MCP Registry).

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for LLM Ops.

    Requires locally running context-bridge-mcp server. Read-only access only. Requires JIRA_API_TOKEN, SENTRY_AUTH_TOKEN, and GITHUB_PERSONAL_ACCESS_TOKEN env vars.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Free to use

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 1 day ago

    • Free with an Agensi account

    Software
    Context Bridge MCPPython

    Requires the Context Bridge MCP server running locally (pip install context-bridge-mcp). Setup guide is in reference/setup.md — about 2 minutes to configure.

    Permissions

    Terminal / Shell
    Network Access

    Requires the Context Bridge MCP server running locally (pip install context-bridge-mcp). Setup guide is in reference/setup.md — about 2 minutes to configure.

    Listed1 day ago

    What's inside

    Frequently Asked Questions

    This skill eliminates context switching by allowing your AI agent to query Jira tickets, Sentry error logs, and GitHub Actions status through a single, unified interface rather than toggling between tabs.

    The skill is built on the Model Context Protocol (MCP), making it compatible with any MCP-enabled AI environment, including Claude Code, Cursor, and IDEs using MCP extensions.

    No, this skill is currently read-only; it is designed to fetch and cross-reference diagnostic data to provide context without the risk of accidentally modifying your tickets or production issues.

    Your purchase includes the full skill configuration for your agent and the necessary documentation to connect to the local Python-based MCP server.

    Security is handled locally; you configure your Jira, Sentry, and GitHub API tokens as environment variables on your own machine, ensuring sensitive credentials are never sent to the LLM provider.

    Setup involves a simple Python package installation via pip, starting a local bridge command, and adding the server endpoint to your agent's MCP configuration file.

    New in LLM Ops

    Free