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/advenimus/syncromsp-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/commands/advenimus/syncromsp-mcp/check-syncro-apis)<a href="https://agentmods.dev/commands/advenimus/syncromsp-mcp/check-syncro-apis"><img src="https://agentmods.dev/badge/commands/advenimus/syncromsp-mcp/check-syncro-apis.svg" alt="Measured on agentmods" 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 | $0.00037 | $0.01716 |
| Opus 5 | $0.00018 | $0.00858 |
| Sonnet 5 | $0.00007 | $0.00343 |
| Haiku 4.5 | $0.00004 | $0.00172 |
Grade A, and why
check-syncro-apis scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL -o "$TMP_SWAGGER" https://api-docs.syncromsp.com/swagger.json How it starts
The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Check Syncro API for new endpoints
You are auditing the SyncroMSP MCP server in this repository for API coverage gaps. The Syncro OpenAPI spec at https://api-docs.syncromsp.com/swagger.json is the source of truth. Your local cached copy lives at docs/swagger.json. The repository's tools live under src/domains/*.ts.
If the user passed --apply (check $ARGUMENTS), implement the additions after producing the report. Otherwise, produce only the report and ask whether to proceed.
Step 1 — Fetch the live spec
Use a temp file outside the repo so we don't dirty the worktree before deciding to update:
TMP_SWAGGER="${TMPDIR:-/tmp}/syncro-swagger-live.json"
curl -fsSL -o "$TMP_SWAGGER" https://api-docs.syncromsp.com/swagger.json
test -s "$TMP_SWAGGER" || { echo "Failed to download spec"; exit 1; }
If the download fails, stop and tell the user.
Step 2 — Diff against the cached spec
Run a Python diff covering three categories of drift:
python3 - <<'PY'
import json, os
tmp = os.environ.get("TMPDIR", "/tmp").rstrip("/") + "/syncro-swagger-live.json"
old = json.load(open("docs/swagger.json"))
new = json.load(open(tmp))
old_paths = old.get("paths", {})
new_paths = new.get("paths", {})
added_paths = sorted(set(new_paths) - set(old_paths))
removed_paths = sorted(set(old_paths) - set(new_paths))
method_diffs = []
for p in sorted(set(old_paths) & set(new_paths)):
om, nm = set(old_paths[p]), set(new_paths[p])
if om != nm:
method_diffs.append((p, sorted(om), sorted(nm)))
def get_params(spec_paths, path, method):
op = spec_paths.get(path, {}).get(method, {})
return {x["name"]: x.get("description", "") for x in op.get("parameters", [])}
def get_body_props(spec_paths, path, method):
op = spec_paths.get(path, {}).get(method, {})
body = op.get("requestBody", {}).get("content", {}).get("application/json", {}).get("schema", {})
return set((body.get("properties") or {}).keys())
param_drift, body_drift = [], []
for p in sorted(set(old_paths) & set(new_paths)):
for m in set(old_paths[p]) & set(new_paths[p]):
added_params = set(get_params(new_paths, p, m)) - set(get_params(old_paths, p, m))
if added_params:
param_drift.append((p, m, sorted(added_params)))
if m in ("post", "put", "patch"):
added_body = get_body_props(new_paths, p, m) - get_body_props(old_paths, p, m)
if added_body:
body_drift.append((p, m, sorted(added_body)))
print("=== ADDED PATHS ===")
for p in added_paths:
print(f" {p} -> {sorted(new_paths[p].keys())}")
print("\n=== REMOVED PATHS ===")
for p in removed_paths:
print(f" {p}")
print("\n=== METHOD CHANGES ===")
for p, o, n in method_diffs:
print(f" {p}: {o} -> {n}")
print("\n=== ADDED QUERY PARAMS ON EXISTING ENDPOINTS ===")
for p, m, params in param_drift:
print(f" {m.upper()} {p}: {', '.join(params)}")
print("\n=== ADDED REQUEST-BODY FIELDS ON EXISTING ENDPOINTS ===")
for p, m, fields in body_drift:
print(f" {m.upper()} {p}: {', '.join(fields)}")
PY
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.
- 8d ago First seen · 144 lines · 37 tokens per session scan A 5134efcafff4
check-syncro-apis is a command published in the GitHub repository advenimus/syncromsp-mcp (10 stars, last pushed 3mo ago), licensed MIT. It adds 37 tokens to every session and 1,716 once invoked, about $0.0002 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 2026-08-31.
Other commands, from other repositories
connector-review
Review DataHub connector code for standards compliance and quality.
review-rust
Focused Rust/Tauri backend review with rust-backend-architect (Primary Owner).
api-style-review
Review SAP API style compliance for REST, OData, OpenAPI, SDK naming, documentation, and lifecycle readiness.
fec-doc-sync
Sync README, docs, environment variables, scripts, API/routing/component descriptions and deployment instructions from code and project sources of truth.
document
On-demand documentation generation — API docs, architecture updates, user guides.
api-review
Review the current code or API against API design principles — identifies violations and suggests improvements.