Gluecron
REMOTE · GLUECRON.COM
AI-native git hosting — repos, PRs, issues, CI gates, and AI code review over MCP (60 tools).
Available components
Last scanned (19 hours ago)
Scores higher than 98% of remote servers
Reachable. Last reached 5 Nov 2026.
Category Version Control
How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →
Endpoint Security94
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- Authorisation is enforced on tool calls, advertised via RFC 9728 protected-resource metadata. Discovery is public, which costs nothing: no tool can be invoked without a token. View diagnostics → Pass
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- The HSTS (Strict-Transport-Security) header is present. View diagnostics → Pass
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
- The authorisation server offers only Dynamic Client Registration (RFC 7591), which MCP 2026-07-28 deprecated in favour of Client ID Metadata Documents. View diagnostics → Partial
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability78
- 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 20012 tokens (~166/item across 120 items; 119 tools + 1 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
- No destabilizing schema changes in the last 30 days.Pass
Tool Coverage91
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 73% of tool parameters carry a description.Partial
Tool Safety99
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- 16 of 17 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "gluecron_list_ready_to_merge" implies "merge" and declares readOnlyHint instead, contradicting what its own name says it does. See how to fix → Partial
- An AI judge read all 120 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities60
- Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28. See how to fix → Fail
Checks we ran (13)
- TLS certificate
- Authorization
- HTTPS
- HSTS header
- DNSSEC
- Transport
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Does not apply to this hosted endpoint (2)
- Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
- Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
The score does not measure everything. What the score does not measure →
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 5 Nov 26 0
- New tool “gluecron_revoke_all_credentials”, which the server declares destructive security
- Tool “gluecron_create_repo_token” rewrote its description, which is the text the model reads security
- Tool “gluecron_get_pr” rewrote its description, which is the text the model reads security
- Tool “gluecron_get_workflow_logs” rewrote its description, which is the text the model reads security
- Tool “gluecron_list_runners” rewrote its description, which is the text the model reads security
- Tool “gluecron_list_workflow_runs” rewrote its description, which is the text the model reads security
- Tool “gluecron_pr_status_summary” rewrote its description, which is the text the model reads security
- Tool “gluecron_resolve_pr_conflict” rewrote its description, which is the text the model reads security
- Tool “gluecron_set_branch_protection” rewrote its description, which is the text the model reads security
- Tool “gluecron_update_repo” rewrote its description, which is the text the model reads security
- New tool “gluecron_propose_pr_conflict_resolution” functional
- “gluecron_update_repo” added an optional parameter “conflict_resolution_mode” cosmetic
- “gluecron_create_repo_token” reworded the description of “permissions” cosmetic
- “gluecron_resolve_pr_conflict” reworded the description of “choices” cosmetic
- 1 Nov 26 0
- Tool “gluecron_create_deploy_token” rewrote its description, which is the text the model reads security
- “gluecron_create_deploy_token” added an optional parameter “deliver” cosmetic
- “gluecron_create_deploy_token” added an optional parameter “token_id” cosmetic
- 29 Oct 26 −1
- Tool “gluecron_ci_health” rewrote its description, which is the text the model reads security
- Tool “gluecron_get_branch_protection” rewrote its description, which is the text the model reads security
- Tool “gluecron_get_pr_checks” rewrote its description, which is the text the model reads security
- Tool “gluecron_list_runners” rewrote its description, which is the text the model reads security
- Destructive annotations: 15 of 16 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "gluecron_list_ready_to_merge" implies "merge" and declares readOnlyHint instead, contradicting what its own name says it does. functional
- New tool “gluecron_list_ready_to_merge” functional
- “gluecron_create_repo_token” reworded the description of “permissions” cosmetic
- 28 Oct 26 0
- Tool “gluecron_create_runner_registration_token” rewrote its description, which is the text the model reads security
- Tool “gluecron_get_pr” rewrote its description, which is the text the model reads security
- Tool “gluecron_get_pr_checks” rewrote its description, which is the text the model reads security
- Tool “gluecron_list_pr_comments” rewrote its description, which is the text the model reads security
- Tool “gluecron_pr_status_summary” rewrote its description, which is the text the model reads security
- Schema quality: 16294 → 18044 ▼ functional
- New tool “gluecron_list_pr_conflicts” functional
- New tool “gluecron_ci_health” functional
- New tool “gluecron_commit_pr_conflict_resolution” functional
- New tool “gluecron_resolve_pr_conflict” functional
- New tool “gluecron_security_ioc_hits” functional
- “gluecron_create_runner_registration_token” added an optional parameter “exclusive” cosmetic
- “gluecron_create_runner_registration_token” added an optional parameter “repositories” cosmetic
- 27 Oct 26 0
- Tool “gluecron_get_workflow_logs” rewrote its description, which is the text the model reads security
- Tool “gluecron_handover” rewrote its description, which is the text the model reads security
- Tool “gluecron_pr_status_summary” rewrote its description, which is the text the model reads security
- 25 Oct 26 0
- New tool “gluecron_delete_branch”, which the server declares destructive security
- New tool “gluecron_delete_comment”, which the server declares destructive security
- New tool “gluecron_edit_comment”, which the server declares destructive security
- 23 Oct 26 0
- Tool “gluecron_set_auto_merge” rewrote its description, which is the text the model reads security
- 22 Oct 26 0
- Tool “gluecron_ci_queue_status” rewrote its description, which is the text the model reads security
- Tool “gluecron_get_workflow_run” rewrote its description, which is the text the model reads security
- Tool “gluecron_prioritize_workflow_run” rewrote its description, which is the text the model reads security
- “gluecron_prioritize_workflow_run” added an optional parameter “level” cosmetic
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 5 Nov 2026 · Probed https://gluecron.com/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=gluecron.com | CN=YR1,O=Let's Encrypt,C=US | 31 Oct 2026 | 29 Jan 2027 | RSA 4096 | SHA256-RSA | 61f97f9651a5996c26d5bdfc43da4535558 |
| SANs: gluecron.com, www.gluecron.com | ||||||
| CN=YR1,O=Let's Encrypt,C=US (CA) | CN=Root YR,O=ISRG,C=US | 3 Sept 2025 | 2 Sept 2028 | RSA 2048 | SHA256-RSA | a20253f15f2691c05dc1ce13b9bcca4e |
| CN=Root YR,O=ISRG,C=US (CA) | CN=ISRG Root X1,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | RSA 4096 | SHA256-RSA | f24b6d17f9d9ad7cb1c9fea78782699f |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of gluecron.com. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | Trust anchor | 20326, 38696 | 8, 8 | Verified |
| com. | DS published | 19718 | 13 | Verified |
| gluecron.com. | No DS | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication Enforced and verified
The endpoint asked for a token and published valid RFC 9728 metadata describing how to get one.
| Result | Enforced and verified |
|---|---|
| Enforced | On tool calls |
| HTTP status | 200 |
WWW-Authenticate challenge Bearer resource_metadata="https://gluecron.com/.well-known/oauth-protected-resource"
Bearer resource_metadata="https://gluecron.com/.well-known/oauth-protected-resource"| Header | Value |
|---|---|
| strict-transport-security | max-age=63072000; includeSubDomains |
| content-security-policy | default-src 'self'; script-src 'self' 'unsafe-inline'; style-src 'self' 'unsafe-inline' https://fonts.googleapis.com; font-src 'self' data: https://fonts.gstatic.com; img-src 'self' data: blob: https:; media-src 'self' data: blob: https:; connect-src 'self' wss://gluecron.com; worker-src 'self' blob:; manifest-src 'self'; frame-src 'self'; frame-ancestors 'self'; base-uri 'self'; object-src 'none' |
| x-content-type-options | nosniff |
| x-frame-options | SAMEORIGIN |
| referrer-policy | strict-origin-when-cross-origin |
| permissions-policy | camera=(), geolocation=(), payment=(), usb=(), microphone=(self) |
Protected resource metadata
| Document | https://gluecron.com/.well-known/oauth-protected-resource |
|---|---|
| Retrieved | Yes |
| Resource | https://gluecron.com/mcp |
| Authorisation server | https://gluecron.com |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://gluecron.com/mcp | Verified | 200 | |
| http (plaintext) | http://gluecron.com/mcp | HTTPS enforced | 301 | https://gluecron.com/mcp |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
gluecron_search_prs ~67
Search pull requests by title/body keyword on a repo.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | number | – | – |
| owner | string | yes | – |
| query | string | yes | – |
| repo | string | yes | – |
| state | string | – | open|closed|merged|all (default open) |
No output schema declared.
No examples provided.
gluecron_search_repos ~187
Search repositories by owner, name, owner/name or description, case-insensitively: every public repo, plus the private ones you own or collaborate on when authenticated. Omit `query` (authenticated) to list YOUR repositories — the ones you own or were invited to — instead of searching. Mirrors GET /api/v2/search/repos. `total` is the full match count (not the page size) and `nextOffset` pages through it.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | number | – | Max rows per page (default 30, max 100) |
| offset | number | – | Rows to skip. Use `nextOffset` from the previous response. |
| query | string | – | Search keyword — matches owner login, repo name, owner/name and description. Omit to list your own repositories. |
| sort | string | – | stars | updated | name (default: stars) |
No output schema declared.
No examples provided.
gluecron_security_ioc_hits ~243
Site admins only (needs an 'admin'-scoped token). Campaign indicator-of-compromise hits: pushes, token uses and repositories that matched a reviewed signature in src/lib/security/campaign-iocs.json (e.g. the Gheist campaign: ci-sync-XXXXXX branches, sync-check.yml, user agent 'gheist'). Filter by signature_id, repository ('owner/name'), since (ISO date); limit (default 50, max 200) / offset. Returns {signatureVersion, signatures, totals, sweep, hits[{id, signatureId, campaign, severity, detectedBy, repository, ref, sha, tokenKind, tokenId, userAgent, evidence, createdAt}]}. Read-only; nothing is revoked.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | number | – | Max rows (default 50, max 200) |
| offset | number | – | Rows to skip |
| repository | string | – | Only hits on this repository, as owner/name |
| signature_id | string | – | Only hits of this signature (e.g. gheist-2026-10) |
| since | string | – | Only hits at or after this ISO date/time |
No output schema declared.
No examples provided.
gluecron_security_scan ~389
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.
| Name | Type | Req | Description |
|---|---|---|---|
| include_ai_review | boolean | – | Opt in to the Claude Sonnet semantic review (SQLi/XSS/SSRF/authz/crypto). Costs an Anthropic call and adds seconds. Default false. When it cannot run — no key, provider error, unparseable output — th… |
| max_candidate_lines | number | – | Cap on lines the secret detector inspects (1-200000, default 20000). The whole tree is always prefiltered; only lines that already matched a secret marker are inspected, so this rarely binds. When it… |
| owner | string | yes | Repo owner username |
| ref | string | – | Branch, tag or commit SHA to scan the tree of. Default: the repo's default branch. Note advisories describe the INDEXED dependency graph, whose commit is reported separately — if it differs from this… |
| repo | string | yes | Repo name |
No output schema declared.
No examples provided.
gluecron_semantic_search ~127
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.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | number | – | – |
| owner | string | yes | – |
| query | string | yes | – |
| repo | string | yes | – |
No output schema declared.
No examples provided.
gluecron_set_auto_merge ~230
Arm (enabled: true) or disarm (enabled: false) auto-merge on one PR: it merges by itself through the full gated merge chain (CI, required checks, branch protection, CODEOWNERS, risk) once CI and every required check are green and no reviewer with write access has changes requested. Stays armed while anything is pending; `last_attempt.reason` says what it waits for. Arming is also the merge train's consent: on a repository with the train on, the train merges only armed PRs, so disarming holds the PR from it (an explicit gluecron_merge_pr still merges). Requires write access and 'repo' scope. merge_method: 'merge' only. Returns {number, auto_merge}.
| Name | Type | Req | Description |
|---|---|---|---|
| enabled | boolean | yes | true = arm, false = disarm |
| merge_method | string | – | 'merge' (default; the only method the gated chain has) |
| number | number | yes | PR number |
| owner | string | yes | Repo owner — username or organisation slug |
| repo | string | yes | Repo name |
No output schema declared.
No examples provided.
gluecron_set_branch_protection ~345
Set branch protection for one branch (partial update: fields you omit keep their value). Edits the rule named exactly after the branch; when only a glob rule covers it, a new exact rule is created seeded from the glob's settings and checks. required_checks replaces the required-check list; it may add checks, but REMOVING a check that applies to the branch is refused here (it needs a step-up: the web page or the REST API with the account password). require_pr_run: a required check that names a workflow is met only by that workflow's pull_request run. Requires ADMIN access to the repo and 'repo' scope. Audit-logged. Returns the resulting rule plus {created, warnings}.
| Name | Type | Req | Description |
|---|---|---|---|
| allow_deletion | boolean | – | – |
| allow_force_push | boolean | – | – |
| branch | string | yes | Branch name (not a pattern) |
| dismiss_stale_reviews | boolean | – | – |
| enable_auto_merge | boolean | – | Branch-wide autopilot auto-merge (K2) |
| owner | string | yes | Repo owner — username or organisation slug |
| repo | string | yes | Repo name |
| require_ai_approval | boolean | – | – |
| require_green_gates | boolean | – | – |
| require_human_review | boolean | – | – |
| require_pr_run | boolean | – | Workflow checks count only from the PR's pull_request run |
| require_pull_request | boolean | – | – |
| required_approvals | number | – | Human approvals required (0-10) |
| required_checks | array | – | Array of check names that must pass (workflow names, gate names or commit-status contexts); [] clears the list |
No output schema declared.
No examples provided.
gluecron_set_pr_draft ~145
Mark a pull request ready for review (draft=false) or convert it back to a draft (draft=true). Same rule as the web 'Ready for review' button: the caller needs write access and must be the PR author or the repository owner; only an open PR changes; marking ready starts the AI review. Idempotent. Requires 'repo' scope. Returns {number, isDraft, changed}.
| Name | Type | Req | Description |
|---|---|---|---|
| draft | boolean | yes | true = convert to draft, false = mark ready for review |
| number | number | yes | PR number |
| owner | string | yes | Repo owner — username or organisation slug |
| repo | string | yes | Repo name |
No output schema declared.
No examples provided.
gluecron_set_repo_secret ~280
Create or replace one workflow secret on a repository, used in workflows as ${{ secrets.NAME }}. The name is saved upper-cased (cron_secret → CRON_SECRET); trailing spaces/newlines are removed from the value. The value is WRITE-ONLY: it is encrypted at rest and never returned, logged or audited — the result names the secret only. Pass expected_updated_at (the updated_at you last read) to update only if nobody changed it since: a newer value is never overwritten (error 'conflict'), a deleted secret is not re-created (error 'missing'). Setting the value it already has writes nothing (result 'unchanged'), so a retry is safe. Needs admin access to the repository and 'repo' scope. Audit-logged (name only). Returns {repository, name, created, result: 'created'|'updated'|'unchanged', updated_at}.
| Name | Type | Req | Description |
|---|---|---|---|
| expected_updated_at | string | – | Optional ISO time: only update if the secret's updated_at is still this (from gluecron_list_repo_secrets) |
| name | string | yes | Secret name: letters, digits, underscores; not starting with a digit |
| owner | string | yes | Repo owner — username or organisation slug |
| repo | string | yes | Repo name |
| value | string | yes | The secret value (never echoed back) |
No output schema declared.
No examples provided.
gluecron_set_variable ~203
Create or replace an Actions variable (plain text, not for secrets — use gluecron_set_repo_secret). Pass owner + repo for a repository variable, owner + repo + environment for an environment variable, or org for an organisation variable (organisation variables need an admin-scoped token). Safe to retry: the same value again changes nothing. Audit-logged. Returns {name, effect: created|updated|unchanged, updatedAt}.
| Name | Type | Req | Description |
|---|---|---|---|
| environment | string | – | Environment name (or id) |
| name | string | yes | Variable name: letters, digits and _, not starting with a digit or GITHUB_ (stored upper-case) |
| org | string | – | Organisation slug |
| owner | string | – | Repo owner — username or organisation slug (omit when passing org) |
| repo | string | – | Repo name |
| value | string | yes | Plain-text value (not a secret: shown on the settings page and in logs), at most 48 KB |
No output schema declared.
No examples provided.
gluecron_ship_spec ~88
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.
| Name | Type | Req | Description |
|---|---|---|---|
| body | string | yes | Spec body (Markdown) |
| owner | string | yes | – |
| repo | string | yes | – |
| title | string | yes | – |
No output schema declared.
No examples provided.
gluecron_trigger_workflow ~99
Dispatch a workflow_dispatch run. Mirrors POST /api/v2/repos/.../actions/workflows/:filename/dispatches. Requires 'repo' scope.
| Name | Type | Req | Description |
|---|---|---|---|
| filename | string | yes | Workflow filename (e.g. ci.yml) |
| inputs | object | – | Workflow inputs (object) |
| owner | string | yes | – |
| ref | string | – | Branch / tag / sha (default: repo default branch) |
| repo | string | yes | – |
No output schema declared.
No examples provided.
gluecron_unlabel_issue ~63
Detach a label from an issue. Idempotent. Requires 'repo' scope. Returns {removed: boolean}.
| Name | Type | Req | Description |
|---|---|---|---|
| label | string | yes | – |
| number | number | yes | – |
| owner | string | yes | – |
| repo | string | yes | – |
No output schema declared.
No examples provided.
gluecron_update_pr ~239
Edit a pull request's title, body, base branch and/or draft state. Title / body / base: the PR's author or anyone with write access; draft: the same rule as gluecron_set_pr_draft (write access and the PR author or repo owner; marking ready starts the AI review). Needs 'repo' scope. Changing the base (open PRs only) re-runs the PR's pull_request CI against the new base and disarms auto-merge. Returns {number, title, body, baseBranch, headBranch, isDraft, changed, autoMergeDisarmed, url}.
| Name | Type | Req | Description |
|---|---|---|---|
| base | string | – | New base branch |
| body | string | – | New body (Markdown); an empty string clears it |
| draft | boolean | – | true = back to draft, false = ready for review (gluecron_set_pr_draft's rule: write access and the PR author or repo owner) |
| number | number | yes | PR number |
| owner | string | yes | Repo owner — username or organisation slug |
| repo | string | yes | Repo name |
| title | string | – | New title |
No output schema declared.
No examples provided.
gluecron_update_pr_branch ~157
Bring a PR branch up to date with its base: merge the base into the head server-side (the PR page's 'Update branch'). Never a force-push — the new head is a merge commit moved through the push gates, so it gets CI. On conflict nothing changes and `conflictFiles` lists the paths. Requires write access and 'repo' scope. Returns {ok, status: 'updated'|'up-to-date', headSha, previousHeadSha, baseSha, url} or {ok: false, reason, message, conflictFiles}.
| Name | Type | Req | Description |
|---|---|---|---|
| number | number | yes | PR number |
| owner | string | yes | Repo owner — username or organisation slug |
| repo | string | yes | Repo name |
No output schema declared.
No examples provided.
gluecron_update_repo ~270
Update repository description / visibility / default_branch / automation dials / merge-conflict AI mode. Requires 'admin' access on the repo (owner, org owners/admins, admin collaborators) and 'repo' scope. Returns {ok: true}.
| Name | Type | Req | Description |
|---|---|---|---|
| automation | object | – | Per-repo automation dials, same keys as Settings → Automation: ai_review_mode, pr_triage_mode, issue_triage_mode, auto_merge_mode, ci_autofix_mode, auto_repair_mode, auto_issues_mode, doc_drift_mode,… |
| conflict_resolution_mode | string | – | Who may settle merge conflicts with AI (Settings → Gates → Merge conflicts): manual (no AI) | review_first (default: AI proposes per block, a person accepts, edits or rejects) | auto_land (saved; act… |
| default_branch | string | – | Set default branch (optional) |
| description | string | – | New description (optional) |
| is_private | boolean | – | Set visibility (optional) |
| owner | string | yes | Repo owner username |
| repo | string | yes | Repo name |
No output schema declared.
No examples provided.
gluecron_voice_to_pr ~94
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.
| Name | Type | Req | Description |
|---|---|---|---|
| as | string | – | 'spec' or 'issue' (default: auto via interpretVoiceTranscript) |
| owner | string | yes | – |
| repo | string | yes | – |
| transcript | string | yes | – |
No output schema declared.
No examples provided.
gluecron_whoami ~80
Who this connector is on this Gluecron instance: the signed-in username and email, whether that account is a site admin, the token's scopes, and how many repositories it owns or collaborates on. Call it first when a repository seems missing — the answer is usually which account authorized the connector. Anonymous callers get authenticated:false and a hint.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
gluecron_write_file ~167
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. Meets the same branch protection, rulesets and secret scan as a git push, and fires CI/webhooks like one. Requires 'repo' scope.
| Name | Type | Req | Description |
|---|---|---|---|
| branch | string | yes | – |
| content | string | – | UTF-8 file body (optional) |
| content_base64 | string | – | Base64 file body (optional) |
| expect_blob_sha | string | – | Optimistic-concurrency check: existing blob sha must match. |
| message | string | yes | Commit message |
| owner | string | yes | – |
| path | string | yes | – |
| repo | string | yes | – |
No output schema declared.
No examples provided.
How do I install the Gluecron MCP server?
Gluecron is a hosted endpoint at https://gluecron.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
remote · gluecron.com
claude mcp add --transport http com-gluecron-gluecron 'https://gluecron.com/mcp'
What is the Gluecron MCP server?
Gluecron is an MCP server listed in the public MCP registry as com.gluecron/gluecron. AI-native git hosting, repos, PRs, issues, CI gates, and AI code review over MCP (60 tools). This page covers its hosted endpoint (https://gluecron.com/mcp).
Is the Gluecron MCP server safe to use?
Gluecron scores 91 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the Gluecron MCP server expose?
Gluecron exposes 119 tools: gluecron_repo_search, gluecron_repo_read_file, gluecron_repo_list_issues, gluecron_repo_explain_codebase, gluecron_repo_health, and 114 more. Their descriptions and schemas cost roughly 19,992 tokens of context every time the server is loaded.
Does the Gluecron MCP server require authentication?
Yes. Gluecron asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.
Is the Gluecron MCP server still maintained?
Gluecron is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What did VerifyMCP test on the Gluecron MCP server?
VerifyMCP ran 13 checks on Gluecron, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.