Graneth
REMOTE · GRANETH.COM · 2 COMPONENTS · SCANNED SEP 20
Pre-flight check for AI coding agents: hallucinated packages + secrets, 6 ecosystems, no account.
Available components
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 Security63
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- Authorisation not fully verified: no authorisation is required to call this server, and 4 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe. See how to fix → View diagnostics → Unverified
- 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
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability62
- 50% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Partial
- AI-judged instruction clarity (good).Pass
- Tool/resource definitions use about 542 tokens (~90/item across 6 items; 4 tools + 2 resources), lean.Pass
- 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 Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 4 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 5 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
How do I install the Graneth MCP server?
Graneth is a hosted endpoint at https://graneth.com/api/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 · graneth.com
claude mcp add --transport http com-graneth-mcp-server 'https://graneth.com/api/mcp'
{
"mcpServers": {
"com-graneth-mcp-server": {
"url": "https://graneth.com/api/mcp"
}
}
} {
"servers": {
"com-graneth-mcp-server": {
"type": "http",
"url": "https://graneth.com/api/mcp"
}
}
} [mcp_servers.com-graneth-mcp-server] url = "https://graneth.com/api/mcp"
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"com-graneth-mcp-server": {
"type": "remote",
"url": "https://graneth.com/api/mcp",
"enabled": true
}
}
} openclaw mcp add com-graneth-mcp-server --url 'https://graneth.com/api/mcp' --transport streamable-http
mcp_servers:
com-graneth-mcp-server:
url: "https://graneth.com/api/mcp" {
"McpServers": {
"com-graneth-mcp-server": {
"Transport": "http",
"Url": "https://graneth.com/api/mcp"
}
}
} assistant mcp add com-graneth-mcp-server -t streamable-http -u 'https://graneth.com/api/mcp'
{
"mcpServers": {
"com-graneth-mcp-server": {
"type": "http",
"url": "https://graneth.com/api/mcp"
}
}
} The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.
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.
- 26 Aug 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 25 Aug 26 +1
- Stability: 0.97 → pass security
- 23 Aug 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.
- 22 Aug 26 76
- Tool “get_findings” rewrote its description, which is the text the model reads security
- 11 Aug 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 31 Jul 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 27 Jul 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 26 Jul 26 0
First indexed and scored.
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 20 Sept 2026 · Probed https://graneth.com/api/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=graneth.com | CN=WE1,O=Google Trust Services,C=US | 4 Sept 2026 | 3 Dec 2026 | ECDSA 256 | ECDSA-SHA256 | 62429c9427c7c2930eff9b141fbe0e23 |
| SANs: graneth.com, *.graneth.com | ||||||
| CN=WE1,O=Google Trust Services,C=US (CA) | CN=GTS Root R4,O=Google Trust Services LLC,C=US | 13 Dec 2023 | 20 Feb 2029 | ECDSA 256 | ECDSA-SHA384 | 7ff31977972c224a76155d13b6d685e3 |
| CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) | CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE | 15 Nov 2023 | 28 Jan 2028 | ECDSA 384 | SHA256-RSA | 7fe530bf331343bedd821610493d8a1b |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of graneth.com. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| com. | present | 19718 | 13 | Verified |
| graneth.com. | absent | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication No authorisation required
The endpoint answered without asking for a token. Anyone who knows the URL can reach it.
| Result | No authorisation required |
|---|---|
| HTTP status | 200 |
| Header | Value |
|---|---|
| strict-transport-security | max-age=31536000; includeSubDomains |
| content-security-policy | default-src 'self';base-uri 'self';font-src 'self' data:;form-action 'self';frame-ancestors 'self';img-src 'self' data:;object-src 'none';script-src 'self';script-src-attr 'none';style-src 'self' 'unsafe-inline';upgrade-insecure-requests;connect-src 'self';frame-src 'none' |
| x-content-type-options | nosniff |
| x-frame-options | SAMEORIGIN |
| referrer-policy | no-referrer |
| permissions-policy | accelerometer=(), camera=(), geolocation=(), gyroscope=(), magnetometer=(), microphone=(), usb=(), interest-cohort=() |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://graneth.com/api/mcp | Verified | 200 | |
| http (plaintext) | http://graneth.com/api/mcp | HTTPS enforced | 301 | https://graneth.com/api/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 →
auto_remediate ~202
Generate an automated security fix for a specific finding. Creates a GitHub PR with the patched code. Verifies the fix with Level 1 SAST before opening the PR. Requires authentication, 3 credits, and ANTHROPIC_API_KEY.
| Name | Type | Req | Description |
|---|---|---|---|
| description | string | yes | Finding description |
| file | string | yes | File path containing the vulnerability (relative, no traversal) |
| finding_type | string | yes | Finding type e.g. 'command_injection', 'sql_injection' |
| line | integer | yes | Line number of the finding |
| owner | string | yes | GitHub repository owner |
| recommendation | string | yes | Recommended fix from scan results |
| ref | string | – | Git ref (branch/SHA) |
| repo | string | yes | GitHub repository name |
| severity | string | yes | Finding severity |
| title | string | yes | Finding title from scan results |
| token | string | yes | GitHub token with repo write access |
No output schema declared.
No examples provided.
get_findings ~116
Retrieve the security findings recorded by your most recent scan of this repository, optionally filtered by exact file path or severity. Returns an error if you have never scanned it — that is not the same answer as no findings. Checks that could not run are reported as a count, never listed among the findings.
| Name | Type | Req | Description |
|---|---|---|---|
| file | string | – | Filter findings to a specific file path |
| owner | string | yes | GitHub repository owner |
| repo | string | yes | GitHub repository name |
| severity | string | – | Filter by severity level |
No output schema declared.
No examples provided.
pre_flight_check ~107
Security pre-flight check for local file changes BEFORE committing. Run this whenever you are about to suggest `git commit`, `git push`, or open a pull request — especially when changes touch auth, secrets, SQL queries, package.json / requirements.txt, or environment variables. Returns CLEAR or BLOCKED with specific findings and remediation steps.
| Name | Type | Req | Description |
|---|---|---|---|
| context | string | – | What these changes do (helps with triage) |
| files | array | yes | Files staged for commit (path + content) |
No output schema declared.
No examples provided.
scan_repository ~108
Trigger a Level 1 + Level 2 security scan on a GitHub pull request. Returns SAST findings, taint flows, entropy-detected secrets, and (for PRO users) LLM-triaged results. Requires Graneth authentication.
| Name | Type | Req | Description |
|---|---|---|---|
| owner | string | yes | GitHub repository owner |
| pull_number | integer | yes | Pull request number to scan |
| repo | string | yes | GitHub repository name |
| token | string | yes | GitHub access token with repo read permissions |
No output schema declared.
No examples provided.
What is the Graneth MCP server?
Graneth is an MCP server listed in the public MCP registry as com.graneth/mcp-server. Pre-flight check for AI coding agents: hallucinated packages + secrets, 6 ecosystems, no account. This page covers its hosted endpoint (https://graneth.com/api/mcp).
Is the Graneth MCP server safe to use?
Graneth scores 78 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 Graneth MCP server expose?
Graneth exposes 4 tools: scan_repository, pre_flight_check, get_findings, auto_remediate. Their descriptions and schemas cost roughly 533 tokens of context every time the server is loaded.
Does the Graneth MCP server require authentication?
No. We connected to Graneth without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the Graneth MCP server still maintained?
Graneth is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.