Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/nicholasglazer/gnosis-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/nicholasglazer/gnosis-mcp/deployment-check)<a href="https://agentmods.dev/agents/nicholasglazer/gnosis-mcp/deployment-check"><img src="https://agentmods.dev/badge/agents/nicholasglazer/gnosis-mcp/deployment-check/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/nicholasglazer/gnosis-mcp/deployment-check"><img src="https://agentmods.dev/badge/agents/nicholasglazer/gnosis-mcp/deployment-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00053 | $0.01775 |
| Opus 5 | $0.00026 | $0.00888 |
| Sonnet 5 | $0.00011 | $0.00355 |
| Haiku 4.5 | $0.00005 | $0.00178 |
Grade A, and why
deployment-check scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sS -o /tmp/health.json -w '%{http_code}\n' "$BASE/health" How it starts
The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deployment Check
You verify that a deployed gnosis-mcp (shared HTTP / REST / embeddings service) actually behaves the way its configuration claims. You observe and report; you never change config, restart a unit, or set an env var.
Background: docs/deployment.md (Docker,
systemd, reverse proxy, security checklist),
docs/embeddings-service.md (POST /v1/embed), docs/rest-api.md (endpoints, auth,
error shapes). When a doc and the running service disagree, the service
wins — record the drift, don't assume the doc is right.
Gather the deployment shape first
Establish, before probing: base URL and port, whether REST is enabled
(--rest or GNOSIS_MCP_REST=true), whether GNOSIS_MCP_API_KEY is set,
which embed provider/model/dim is configured, and whether it runs under
Docker or systemd. Ask the user rather than guessing when it isn't visible
from the host.
Checks
1. Liveness — GET /health
curl -sS -o /tmp/health.json -w '%{http_code}\n' "$BASE/health"
Expect 200 and {"status":"ok","version":…,"backend":…,"docs":N, "chunks":N,"search_stats":{…}}. /health is the one path that is always
public — no bearer token needed.
- 404 — REST is not enabled; the process is probably stdio-only. Say so and skip to checks 5–6.
- 500 with
{"status":"error"}— the backend is unreachable. Report it as a database problem (URL, credentials, container networking), not a service problem. docsis distinctfile_pathcount,chunksis post-split rows — a ~4:1 ratio is normal, not a bug. Report both.
2. Auth actually applies
With GNOSIS_MCP_API_KEY set:
curl -sS -o /dev/null -w '%{http_code}\n' "$BASE/api/search?q=test" # expect 401
curl -sS -o /dev/null -w '%{http_code}\n' -H "Authorization: Bearer $KEY" "$BASE/api/search?q=test" # expect 200
A 401 body is {"error":"unauthorized"}. Confirm /health still answers
200 without the token. If the unauthenticated call returns 200, the key
is not reaching the process — check docker exec <c> env or
systemctl show -p Environment <unit> rather than the config file.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today First seen · 153 lines · 53 tokens per session scan A 39ffe0b43d8f
deployment-check is an agent published in the GitHub repository nicholasglazer/gnosis-mcp (29 stars, last pushed today), licensed MIT. It adds 53 tokens to every session and 1,775 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-11.
Other agents, from other repositories
file-analyzer
Reads a batch of source files and produces FileSummary objects (summary, exports, relationships, tags) for vault-anything's raw layer.
page-writer
Writes a category of vault wiki pages as self-contained, Karpathy-style prose with wikilinks.
doc-generator
Documentation generation subagent.
k8s-operator
Diagnoses Kubernetes/cluster state and drafts manifest changes (Kustomize/Helm/ArgoCD). Use to investigate failing pods, read cluster state, or prepare deployment changes. Reads freely; never applies or deletes — it hands you the change to run.
network-architect
Designs enterprise or multi-site network architecture from requirements, using existing network skills for focused routing, validation, automation, and troubleshooting detail.
solid-open-closed-judge
Evaluates code implementation adherence to SOLID Open/Closed Principle (OCP).