ground_citation
shallowcom.astranl/mcp · Verify this server
Check one scientific reference before you reuse or cite it, with ONE call. Give a DOI. AstraNL reads the Crossref work record and every Crossref notice that updates it, the OpenAlex retraction flag and the Europe PMC publication types and retraction, erratum and concern links, and returns a status: RETRACTION_NOTICE_FOUND, EXPRESSION_OF_CONCERN_FOUND, CORRECTION_NOTICE_FOUND, NO_NOTICE_IN_CHECKED_SOURCES or NOT_FOUND_IN_CHECKED_SOURCES, with each notice DOI, type and date, the source URLs and the observation time. Every fresh answer carries a SHA-256 digest sealed with the AstraNL moment seal and an AstraLock event id you can check later with verify_astranl. Limits: registry data at the observed time, never a judgement of the science; NO_NOTICE_IN_CHECKED_SOURCES means only these three registries; answers are cached for 24 hours. Never contacts authors or publishers. Writes (why the tool is not read-only): each fresh answer, not one served from the 24 hour cache, appends one event to the public AstraLock log with the DOI, the digest and the status, so the answer can be verified later, and stores the answer in an AstraNL database table (citation_groundings) that serves the cache and counts the budget; the row names only the door (mcp), nothing about the caller. Live budget: 300 fresh reads a day across all MCP callers; after that only cached answers, status DAILY_LIVE_BUDGET_SPENT. Logging: every MCP call is journaled with the tool name, outcome, argument length, caller class (external, probe, crawler, self), a SHA-256 hash of the caller network /24 and the client family; for demand statistics also the first 160 characters of a query, question, title or id argument and the user-agent; never the address itself, other arguments or an account.
1 trials · measured 10 days ago
ground_citation scores 100.0/100 on Vouch's measured behaviour index, from 1 real invocation trials against com.astranl/mcp, measured 12 Nov 2026 under methodology v0.2.0. Every measured component scored 100.
Component breakdown
| Component | Weight | Value |
|---|---|---|
| Reliability | 35% | not applicable |
| Schema integrity | 25% | 100.0 |
| Failure behaviour | 15% | not applicable |
| Latency | 15% | not applicable |
| Concurrency | 10% | not applicable |
Tool details
- Transport
- remote
- Credential class
- open
- Input schema
- not declared
- Output schema
- not declared
- Side-effect classification
- unclassified
Score history
| Day | Score | Tier | Methodology |
|---|---|---|---|
| 2026-11-12 | 100.0 | shallow | v0.2.0 |
Probe evidence
| Probe | Outcomes |
|---|---|
| schema_integrity | pass: 1 |
Raw request/response logs are not archived yet — the outcome counts above are drawn directly from every recorded trial.
Embed this score
Available for every tool, scored or not — not a verification perk. Always links back to this page.
[](https://vouch.tools/tools/fd6ea345-5ea9-4df7-957b-58362d7eff51)