Gluecron

Name: Gluecron
Author: gluecron

Gluecron: git-хостинг для AI-агентов — репозитории, PR, issues и код-ревью в 60 инструментах

От сообществаРаботаетБез входаГлобальныйБесплатноТолько чтение

Что умеет

Искать и читать код в репозиториях
Создавать и комментировать issues и пул-реквесты
Мерджить, закрывать и форкать репозитории
Ставить метки и назначать исполнителей
Запрашивать изменения в код-ревью

Какие данные видит

Ассистент получает доступ к репозиториям и задачам аккаунта Gluecron в рамках прав пользователя.

Нужен ли аккаунт

Не нужен: сервер работает без входа

MCP-сервер даёт AI-агенту полноценный доступ к git-хостингу Gluecron — работу с репозиториями, issues, пул-реквестами и проверками CI. Ассистент читает код, объясняет структуру проекта и ведёт ревью прямо в переписке.

Как подключить

Как подключить Gluecron к Claude

Адрес сервера, который нужно вставить в настройках Claude:

https://gluecron.com/mcp

Откройте Claude (сайт claude.ai или приложение для компьютера).
Перейдите в Настройки → Коннекторы (в английском интерфейсе: Settings → Connectors).
Нажмите Добавить пользовательский коннектор (Add custom connector).
Вставьте адрес сервера, скопированный ниже, в поле URL удалённого MCP-сервера и нажмите Добавить.
В чате нажмите + → Коннекторы и включите новый коннектор.

Пользовательские коннекторы доступны на тарифах Free, Pro, Max, Team и Enterprise. На Free можно добавить только один. В Team и Enterprise коннектор сначала добавляет владелец организации в Настройки организации → Коннекторы.

Авторизация

После нажатия Добавить откроется окно входа в сервис. Войдите под своим аккаунтом и подтвердите доступ. Пароль Claude не видит.

Как подключить Gluecron к ChatGPT

Адрес сервера, который нужно вставить в настройках ChatGPT:

https://gluecron.com/mcp

Откройте ChatGPT в браузере (chatgpt.com). Нужен тариф Plus, Pro, Business, Enterprise или Edu.
Один раз включите режим разработчика: Настройки → Приложения → Дополнительные настройки → Режим разработчика (Settings → Apps → Advanced settings → Developer mode).
Откройте Настройки → Коннекторы и нажмите Создать (Create).
Заполните форму: Название (любое), Описание (одна фраза, что делает сервис), URL MCP-сервера (скопируйте ниже).
В поле Аутентификация выберите OAuth, если сервис требует вход, иначе Нет. Нажмите Создать.
В новом чате откройте + → Приложения/Коннекторы и включите коннектор.

Название раздела у OpenAI менялось (Connectors → Apps/Plugins). Если пункт называется иначе, ищите «режим разработчика» в настройках. В рабочих пространствах Business/Enterprise администратор должен разрешить пользовательские коннекторы.

Авторизация

При первом использовании ChatGPT откроет окно входа в сервис. Войдите и подтвердите доступ.

Как подключить Gluecron к Cursor

Адрес сервера, который нужно вставить в настройках Cursor:

https://gluecron.com/mcp

Быстрый способ: нажмите кнопку Открыть в Cursor ниже, Cursor сам предложит добавить сервер.

Вручную:

В Cursor откройте Settings → Cursor Settings → MCP и нажмите Add new global MCP server.
Вставьте JSON, скопированный ниже, в открывшийся файл ~/.cursor/mcp.json (для одного проекта: .cursor/mcp.json в корне проекта).
Сохраните файл. Сервер появится в списке MCP; при необходимости пройдите авторизацию по кнопке рядом с ним.

Авторизация

Если сервис требует вход, рядом с сервером в списке MCP появится кнопка авторизации.

Список инструментов сервера (62)

Технические названия из tools/list. Нужны только разработчикам.

gluecron_repo_search	Search Gluecron repositories by keyword (name + description), case-insensitively. Returns public repos plus any private repos owned by the authenticated caller. Default 20 per page, max 50; `total` is the full match count and `nextOffset` pages through it.
gluecron_repo_read_file	Read a single file from a repository at a given ref (branch / tag / commit). Private repos are readable when the authenticated caller has access. Returns the text content (binary files rejected).
gluecron_repo_list_issues	List open issues for a public repository. Returns up to 50 ordered by most-recent.
gluecron_repo_explain_codebase	Return the cached AI 'explain this codebase' Markdown for a public repo (most recent commit). Returns null when no cached explanation exists yet.
gluecron_repo_health	Compute the current health report for a public repo: overall score (0-100), letter grade, per-category breakdown (security/testing/complexity/dependencies/documentation/activity), and a list of insights to fix next. Backed by computeHealthScore in src/lib/intelligence.ts.
gluecron_create_issue	Create a new issue on a Gluecron repository. Requires authenticated caller with write access on the target repo. Returns {number, url}.
gluecron_comment_issue	Add a comment to an existing issue. Requires authenticated caller with write access. Returns {commentId}.
gluecron_close_issue	Close an open issue. Requires authenticated caller with write access. Idempotent — closing an already-closed issue is a no-op. Returns {state}.
gluecron_reopen_issue	Reopen a previously closed issue. Requires authenticated caller with write access. Idempotent. Returns {state}.
gluecron_create_pr	Open a new pull request. `head_branch` is required; `base_branch` defaults to the repo default branch. Requires authenticated caller with write access. Returns {number, url}.
gluecron_get_pr	Fetch the full detail record of a pull request (title, body, state, branches, draft, author, timestamps). Authenticated callers only (the read tool surface still works anonymously).
gluecron_list_prs	List pull requests on a repo, filtered by state (open\|closed\|merged\|all). Authenticated callers only. Returns up to 50 summary rows.
gluecron_comment_pr	Add a comment to a pull request. Requires authenticated caller with write access. Returns {commentId}.
gluecron_merge_pr	Merge an open PR. Enforces the same checks as the HTTP merge flow: not a draft, head SHA resolves, GateTest+AI-review hard gates pass, branch-protection rules satisfied. M3: soft-blocks when the pre-merge risk score is `critical` unless `confirm_high_risk: true` is passed. Returns {merged, sha?, reason?, riskScore?}.
gluecron_close_pr	Close an open pull request without merging. Requires authenticated caller with write access. Idempotent. Returns {state}.
gluecron_fork_repo	Fork a repository to the authenticated caller's namespace. Mirrors POST /:owner/:repo/fork. Returns {owner, repo, url}. Requires 'repo' scope.
gluecron_delete_repo	Permanently delete a repository row (git data on disk is left untouched). Requires 'admin' access on the repo (owner, org owners/admins, admin collaborators) AND 'admin' token scope. Returns {deleted: true}.
gluecron_update_repo	Update repository description / visibility / default_branch. Requires 'admin' access on the repo (owner, org owners/admins, admin collaborators) and 'repo' scope. Returns {ok: true}.
gluecron_search_repos	Full-text search of public repositories by name/description, case-insensitively. Mirrors GET /api/v2/search/repos. `total` is the full match count (not the page size) and `nextOffset` pages through it.
gluecron_clone_url	Return the authenticated HTTPS clone URL for a repo + a credential-helper hint. Use this instead of embedding tokens in URLs. Returns {url, hint}.
gluecron_label_issue	Attach one or more labels to an issue. Labels are created if they don't yet exist on the repo. Requires 'repo' scope. Returns {labels}.
gluecron_unlabel_issue	Detach a label from an issue. Idempotent. Requires 'repo' scope. Returns {removed: boolean}.
gluecron_assign_issue	Assign an issue to a user. Gluecron does not yet have a dedicated assignee table; assignment is modelled as an `assignee:<username>` label so it integrates with existing label tooling. Requires 'repo' scope.
gluecron_search_issues	Search issues by title/body keyword on a single repo, filtered by state. Returns ranked rows.
gluecron_request_changes	Post a 'changes requested' AI-review comment on a PR. The comment is tagged with isAiReview=true so the gate-checker recognises it. Requires 'repo' scope.
gluecron_search_prs	Search pull requests by title/body keyword on a repo.
gluecron_open_draft_pr	Open a draft pull request. Same payload as gluecron_create_pr but forces is_draft=true. Useful for AI-in-progress PRs that shouldn't run mergeability checks yet.
gluecron_generate_pr_description	Generate an AI commit-message-style description for a diff. Uses src/lib/ai-commit-message.ts under the hood; gracefully degrades to a heuristic when ANTHROPIC_API_KEY is missing. Returns {subject, body}.
gluecron_read_file	Read a file from a repo at a given ref. Mirrors GET /api/v2/repos/:owner/:repo/contents/:path. Returns {path, size, content, encoding}.
gluecron_write_file	Create or update a file on a branch via git plumbing. Wraps `createOrUpdateFileOnBranch`. Pass `content` as a UTF-8 string OR `content_base64` for binary. Requires 'repo' scope.
gluecron_delete_file	Delete a file from a branch via git plumbing. Requires the existing blob sha (optimistic concurrency) and 'repo' scope. Mirrors DELETE /api/v2/contents.
gluecron_list_tree	List directory contents at a ref. `path` scopes the listing to a subtree and is honoured in BOTH modes; `recursive: true` walks the whole subtree instead of one level. Always returns the same shape: {path, ref, recursive, entries, truncated, totalCount}. Recursive entries carry full repo-relative paths; non-recursive entries carry names. A ref that does not exist is an error, never an empty listing.
gluecron_get_commit	Fetch a single commit by SHA: metadata plus the list of files it changed (path, status, additions, deletions). Mirrors GET /api/v2/repos/.../commits/:sha. Patch bodies are NOT included — use gluecron_get_diff for those.
gluecron_get_diff	Read the actual changes in a commit or a branch range. Pass `sha` for one commit against its first parent, or `base`+`head` for everything head adds since the merge base (what a PR proposes). Returns {files:[{path, oldPath?, status, additions, deletions, binary, patch, patchTruncated}], stats, truncated}. Patch text is byte-capped; set include_patch=false for a files-changed summary only.
gluecron_create_branch	Create a new branch ref pointing at an existing sha. Mirrors POST /api/v2/repos/.../git/refs. Requires 'repo' scope. Returns {ref, sha}.
gluecron_atomic_multi_file_commit	Apply a set of file writes + deletes as a single atomic commit on a branch (creates the branch if it doesn't exist). The killer agent tool: blob/tree/commit/ref-update sequence. Each change is `{path, content?, content_base64?, deleted?}`. Requires 'repo' scope.
gluecron_ship_spec	Drop a spec file in .gluecron/specs/ with status: ready so the autopilot picks it up. Wraps voice-to-pr.shipAsSpec — handle both voice + manual specs. Requires 'repo' scope.
gluecron_voice_to_pr	Interpret a free-form voice transcript and either ship it as a spec or create an issue (caller picks via `as`). Wraps src/lib/voice-to-pr.ts. Requires 'repo' scope.
gluecron_refactor_across_repos	Plan + execute a refactor that spans multiple repos owned by the caller. Wraps src/lib/multi-repo-refactor.ts. `dry_run: true` returns the plan only. Requires 'repo' scope.
gluecron_explain_repo	Return the cached AI 'explain this codebase' Markdown for a repo. Pure read — never triggers a new generation (use the web UI for that).
gluecron_chat_with_repo	Start a new chat with a repo: creates a chat row, sends the first user message, streams + persists the assistant reply. Returns {chat_id, reply}. If the AI service does not answer this fails with a JSON-RPC error carrying {chat_id, ai_error} — it never returns apology copy as a reply. Requires authentication.
gluecron_chat_continue	Send another message to an existing repo chat. Returns the assistant's reply. If the AI service does not answer this fails with a JSON-RPC error carrying {chat_id, ai_error} rather than returning apology copy as a reply.
gluecron_generate_tests	Generate tests for a PR via Claude. Wraps src/lib/ai-test-generator.generateTestsForPr. Mode 'follow-up-pr' opens a new PR; 'append-commit' commits onto the head branch. Requires 'repo' scope.
gluecron_generate_commit_message	Generate a commit message for a diff. Same engine as gluecron_generate_pr_description but explicit for the commit-message use case.
gluecron_generate_release_notes	Generate release notes between two tags. Wraps src/lib/ai-release-notes.generateReleaseNotes. Returns the rendered Markdown + section data.
gluecron_propose_migration	Propose a dependency-upgrade PR. Wraps src/lib/migration-assistant.proposeMajorMigration. Requires 'repo' scope.
gluecron_propose_doc_update	Manual trigger for the AI doc-update flow: scans tracked sections on the default branch and opens a PR rewriting stale prose. Requires 'repo' scope.
gluecron_trigger_workflow	Dispatch a workflow_dispatch run. Mirrors POST /api/v2/repos/.../actions/workflows/:filename/dispatches. Requires 'repo' scope.
gluecron_get_workflow_run	Fetch a workflow run's metadata + status. Mirrors GET /api/v2/repos/.../actions/runs/:id.
gluecron_get_workflow_logs	Return concatenated per-job logs for a workflow run, plus per-job metadata. JSON-friendly companion to the ZIP-download endpoint.
gluecron_cancel_workflow_run	Cancel a queued/running workflow run. Requires 'repo' scope.
gluecron_get_preview_url	Return the branch-preview URL + status for a (repo, branch) pair. Wraps branch-previews.getPreviewForBranch. Returns {ok:false, reason:'not enabled on this host'} when the host has no PREVIEW_DOMAIN (no preview would ever resolve).
gluecron_provision_pr_sandbox	Provision (or re-provision) a sandbox for a PR. Wraps pr-sandbox.provisionSandbox. Requires 'repo' scope. Returns {ok:false, reason:'not enabled on this host'} when no sandbox provisioner runs on the host.
gluecron_create_agent_session	Mint a new agent-multiplayer session. Returns the plaintext `token` exactly once (store it). Requires 'admin' scope.
gluecron_acquire_lease	Grab an exclusive lease on a target (e.g. a PR or branch) for an agent session. Returns null when another agent holds an active lease.
gluecron_release_lease	Release a lease by id. Idempotent. Returns {released}.
gluecron_get_agent_budget	Return spent / cap / remaining cents for an agent session.
gluecron_semantic_search	Query the per-repo vector index (Voyage embeddings when configured, hash fallback otherwise). Reads the live per-push index (code_embeddings) first, falling back to the manually-reindexed chunk index (code_chunks). Returns {hits, source, indexed, indexedFiles} — `indexed: false` means the repo has never been indexed (empty hits are NOT 'no match'); `indexedFiles` is the live-index row count.
gluecron_find_symbol	Find definitions of a symbol by name within a repo. Wraps src/lib/symbols.findDefinitions.
gluecron_pr_status_summary	Compute a one-shot status summary for a PR: state, risk score, AI-review verdicts (trio), gate signals. Read-only.
gluecron_ai_cost_summary	Return AI spend rollups. Scope by one of: user_id (self), repo {owner,repo}, or agent_session_id. Defaults to caller's user spend.
gluecron_security_scan	Everything Gluecron actually knows about a repository's security, in one honest call: OSV.dev CVE/GHSA advisories against the indexed dependency graph (with FIXED VERSIONS), Gluecron's supplemental advisory list, a full-tree committed-secret scan, and optionally a Claude semantic code review. Unlike gluecron_repo_health, an empty result is NEVER reported as a pass: every category returns status 'assessed' \| 'partial' \| 'not_assessed' \| 'error' with a machine-readable reason code, so you can tell 'we checked and it is clean' from 'we never looked'. In particular, a repo whose dependency graph was never indexed returns dependency_advisories.status='not_assessed' (reason 'dependency_graph_not_indexed'), not an empty advisory list. Read-only.