// SCAN REPORT

Gluecron

60 tools. 35 can modify or destroy data without limits.

2 destructive tools with no built-in limits. Policy required.

Last updated: 5 Aug 2026

35 can modify or destroy data

25 read-only

60 tools total

Community server · catalogue entry checked 05/08/2026 · full schemas captured for 60 of 60 tools

How to control Gluecron ↓

TOOL MAP

What Gluecron exposes to your agents

Read (25) Write / Execute (33) Destructive / Financial (2)

Running more than one server? Check your whole stack →

CONTEXT-WINDOW COST

What Gluecron costs in tokens

6,190 tokens of tool definitions, loaded on every request

3.1% of a 200k context window

181 heaviest tool: gluecron_write_file

Full per-tool breakdown → Model it in the token calculator →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Gluecron tools

Destructive · High gluecron_delete_file This tool irreversibly deletes files from a git repository. Destructive · High gluecron_delete_repo This tool irreversibly removes a repository record from the system. Execute · High gluecron_cancel_workflow_run Cancelling a running CI workflow interrupts execution and affects deployment pipelines irreversibly in context. Execute · High gluecron_trigger_workflow This tool triggers CI/CD workflows, which execute code and arbitrary operations in the repository context.

35 of Gluecron's 60 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Gluecron

PolicyLayer is an MCP gateway — it sits between your AI agents and Gluecron, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "gluecron_delete_file": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "gluecron_acquire_lease": {
    "limits": [
      {
        "counter": "gluecron_acquire_lease_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "gluecron_ai_cost_summary": {
    "limits": [
      {
        "counter": "gluecron_ai_cost_summary_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Gluecron — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON GLUECRON →

Instant setup, no code required.

FULL CATALOGUE

All 60 Gluecron tools

DESTRUCTIVE 2 tools

Destructive gluecron_delete_file Delete a file from a branch via git plumbing. Requires the existing blob sha (optimistic concurrency) and 'rep Destructive gluecron_delete_repo Permanently delete a repository row (git data on disk is left untouched). Owner-only. Requires 'admin' scope.

EXECUTE 6 tools

Execute gluecron_cancel_workflow_run Cancel a queued/running workflow run. Requires 'repo' scope. Execute gluecron_generate_tests Generate tests for a PR via Claude. Wraps src/lib/ai-test-generator.generateTestsForPr. Mode 'follow-up-pr' op Execute gluecron_merge_pr Merge an open PR. Enforces the same checks as the HTTP merge flow: not a draft, head SHA resolves, GateTest+AI Execute gluecron_provision_pr_sandbox Provision (or re-provision) a sandbox for a PR. Wraps pr-sandbox.provisionSandbox. Requires 'repo' scope. Execute gluecron_refactor_across_repos Plan + execute a refactor that spans multiple repos owned by the caller. Wraps src/lib/multi-repo-refactor.ts. Execute gluecron_trigger_workflow Dispatch a workflow_dispatch run. Mirrors POST /api/v2/repos/.../actions/workflows/:filename/dispatches. Requi

WRITE 27 tools

Write gluecron_acquire_lease Grab an exclusive lease on a target (e.g. a PR or branch) for an agent session. Returns null when another agen Write gluecron_assign_issue Assign an issue to a user. Gluecron does not yet have a dedicated assignee table; assignment is modelled as an Write 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 e Write gluecron_chat_continue Send another message to an existing repo chat. Returns the assistant's reply. Write gluecron_chat_with_repo Start a new chat with a repo: creates a chat row, sends the first user message, streams + persists the assista Write gluecron_close_issue Close an open issue. Requires authenticated caller with write access. Idempotent — closing an already-closed i Write gluecron_close_pr Close an open pull request without merging. Requires authenticated caller with write access. Idempotent. Retur Write gluecron_comment_issue Add a comment to an existing issue. Requires authenticated caller with write access. Returns {commentId}. Write gluecron_comment_pr Add a comment to a pull request. Requires authenticated caller with write access. Returns {commentId}. Write gluecron_create_agent_session Mint a new agent-multiplayer session. Returns the plaintext token exactly once (store it). Requires 'admin' sc Write gluecron_create_branch Create a new branch ref pointing at an existing sha. Mirrors POST /api/v2/repos/.../git/refs. Requires 'repo' Write gluecron_create_issue Create a new issue on a Gluecron repository. Requires authenticated caller with write access on the target rep Write gluecron_create_pr Open a new pull request. head_branch is required; base_branch defaults to the repo default branch. Requires au Write gluecron_fork_repo Fork a repository to the authenticated caller's namespace. Mirrors POST /:owner/:repo/fork. Returns {owner, re Write gluecron_generate_pr_description Generate an AI commit-message-style description for a diff. Uses src/lib/ai-commit-message.ts under the hood; Write 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' Write gluecron_open_draft_pr Open a draft pull request. Same payload as gluecron_create_pr but forces is_draft=true. Useful for AI-in-progr Write gluecron_propose_doc_update Manual trigger for the AI doc-update flow: scans tracked sections on the default branch and opens a PR rewriti Write gluecron_propose_migration Propose a dependency-upgrade PR. Wraps src/lib/migration-assistant.proposeMajorMigration. Requires 'repo' scop Write gluecron_release_lease Release a lease by id. Idempotent. Returns {released}. Write gluecron_reopen_issue Reopen a previously closed issue. Requires authenticated caller with write access. Idempotent. Returns {state} Write gluecron_request_changes Post a 'changes requested' AI-review comment on a PR. The comment is tagged with isAiReview=true so the gate-c Write gluecron_ship_spec Drop a spec file in .gluecron/specs/ with status: ready so the autopilot picks it up. Wraps voice-to-pr.shipAs Write gluecron_unlabel_issue Detach a label from an issue. Idempotent. Requires 'repo' scope. Returns {removed: boolean}. Write gluecron_update_repo Update repository description / visibility / default_branch. Owner-only. Requires 'repo' scope. Returns {ok: t Write 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). Write gluecron_write_file Create or update a file on a branch via git plumbing. Wraps createOrUpdateFileOnBranch. Pass content as a UTF-

READ 25 tools

Read gluecron_ai_cost_summary Return AI spend rollups. Scope by one of: user_id (self), repo {owner,repo}, or agent_session_id. Defaults to Read gluecron_clone_url Return the authenticated HTTPS clone URL for a repo + a credential-helper hint. Use this instead of embedding Read gluecron_explain_repo Return the cached AI 'explain this codebase' Markdown for a repo. Pure read — never triggers a new generation Read gluecron_find_symbol Find definitions of a symbol by name within a repo. Wraps src/lib/symbols.findDefinitions. Read gluecron_generate_commit_message Generate a commit message for a diff. Same engine as gluecron_generate_pr_description but explicit for the com Read gluecron_generate_release_notes Generate release notes between two tags. Wraps src/lib/ai-release-notes.generateReleaseNotes. Returns the rend Read gluecron_get_agent_budget Return spent / cap / remaining cents for an agent session. Read gluecron_get_commit Fetch a single commit's metadata by SHA. Mirrors GET /api/v2/repos/.../commits/:sha. Read gluecron_get_pr Fetch the full detail record of a pull request (title, body, state, branches, draft, author, timestamps). Auth Read gluecron_get_preview_url Return the branch-preview URL + status for a (repo, branch) pair. Wraps branch-previews.getPreviewForBranch. Read gluecron_get_workflow_logs Return concatenated per-job logs for a workflow run, plus per-job metadata. JSON-friendly companion to the ZIP Read gluecron_get_workflow_run Fetch a workflow run's metadata + status. Mirrors GET /api/v2/repos/.../actions/runs/:id. Read gluecron_list_prs List pull requests on a repo, filtered by state (open|closed|merged|all). Authenticated callers only. Returns Read gluecron_list_tree List directory contents at a ref. Optionally recursive: true returns the full file list. Mirrors GET /api/v2/r Read gluecron_pr_status_summary Compute a one-shot status summary for a PR: state, risk score, AI-review verdicts (trio), gate signals. Read-o Read gluecron_read_file Read a file from a repo at a given ref. Mirrors GET /api/v2/repos/:owner/:repo/contents/:path. Returns {path, Read gluecron_repo_explain_codebase Return the cached AI 'explain this codebase' Markdown for a public repo (most recent commit). Returns null whe Read gluecron_repo_health Compute the current health report for a public repo: overall score (0-100), letter grade, per-category breakdo Read gluecron_repo_list_issues List open issues for a public repository. Returns up to 50 ordered by most-recent. Read gluecron_repo_read_file Read a single file from a repository at a given ref (branch / tag / commit). Private repos are readable when t Read gluecron_repo_search Search Gluecron repositories by keyword (name + description). Returns public repos plus any private repos owne Read gluecron_search_issues Search issues by title/body keyword on a single repo, filtered by state. Returns ranked rows. Read gluecron_search_prs Search pull requests by title/body keyword on a repo. Read gluecron_search_repos Full-text search of public repositories by name/description. Mirrors GET /api/v2/search/repos. Returns ranked Read gluecron_semantic_search Query the per-repo vector index (Voyage embeddings when configured, hash fallback otherwise). Wraps src/lib/se

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Gluecron

Can an AI agent delete data through the Gluecron MCP server? +

Yes. The Gluecron server exposes 2 destructive tools including gluecron_delete_file, gluecron_delete_repo. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Gluecron? +

The Gluecron server has 27 write tools including gluecron_acquire_lease, gluecron_assign_issue, gluecron_atomic_multi_file_commit. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Gluecron.

How many tools does the Gluecron MCP server expose? +

60 tools across 4 categories: Destructive, Execute, Read, Write. 25 are read-only. 35 can modify, create, or delete data.

How do I enforce a policy on Gluecron? +

Register the Gluecron MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Gluecron tool call.

Deterministic rules across all 60 Gluecron tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON GLUECRON →

Instant setup, no code required.

60 Gluecron tools catalogued and risk-classified — across an index of 46,500+ MCP servers.

// WHERE THIS COMES FROM

These policies come from Gluecron's registry record.

The record behind this page: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →