Prévient les hallucinations de l'IA dans les données financières et ERP en traçant chaque chiffre vers les lignes spécifiques de sa source de base de données.
Aussi connu sous brick-byte/footnote, @brick-byte/footnote
- Étoiles
- 0
- Outils
- —
- Téléchargements, 30 jours
- 819
- Dernière version
- 0.2.0
- Dernier commit
- 4 nov. 2026
- Licence
- MIT
Qu'est-ce que footnote MCP ?
Prévient les hallucinations de l'IA dans les données financières et ERP en traçant chaque chiffre vers les lignes spécifiques de sa source de base de données.
Résumé généré à partir du README du projet
À propos du MCP server footnote
Les analystes financiers et les développeurs travaillant avec des données ERP peuvent utiliser footnote pour prévenir les hallucinations de l'IA en garantissant que chaque chiffre est tracé jusqu'aux lignes de base de données spécifiques. Au lieu de permettre à un modèle de langage de générer des nombres, ce serveur utilise un noyau déterministe où le modèle sélectionne des opérations dans un catalogue typé et où le SQL gère toutes les agrégations. Cela garantit que les valeurs sont copiées textuellement depuis le système de référence plutôt que d'être inventées par le modèle.
Le serveur fonctionne à la fois comme un MCP server et un magasin de provenance, nécessitant une connexion en lecture seule à votre base de données ERP et une base de données séparée en mode append-only pour la piste d'audit. Il est compatible avec des clients tels que Claude Desktop, Cursor et LangChain. Pour maintenir l'intégrité des données, le serveur impose un journal de provenance infalsifiable par chaînage de hashs écrit côté serveur, ce qui signifie que le modèle ne peut pas influencer la piste d'audit. Cette configuration fournit des citations cliquables et des preuves exportables pour les auditeurs, ce qui la rend adaptée aux environnements de gestion des stocks ou des achats à enjeux élevés.
Ce que vous pouvez faire avec
- 1Vérification d'affirmations financièresUn auditeur peut cliquer sur un montant monétaire dans une réponse de l'IA pour voir les enregistrements de factures exacts qui ont produit le total.
- 2Prévention de la fabrication de données clientsSi un modèle tente d'interroger un client inexistant, le serveur renvoie une erreur récupérable avec de réelles alternatives au lieu de laisser le modèle inventer une histoire.
- 3Audit du raisonnement de l'IALorsqu'une IA fournit un jugement sur un risque, le serveur décompose la conclusion en faits vérifiables et cités séparément.
- 4Garantie de l'intégrité des donnéesLes développeurs peuvent exécuter une commande de vérification pour s'assurer que personne n'a modifié les journaux d'audit historiques.
Extrait du README du projet. Chaque cas d'utilisation est vérifié par rapport à une citation du document.
Comment installer footnote MCP
Formats vérifiés le 10 nov. 2026Ajouter à CursorAjouter à GooseInstaller footnote MCP dans Claude Code
$ claude mcp add --env 'DATABASE_URL=<YOUR_DATABASE_URL>' footnote -- npx -y @brick-byte/footnoteInstaller footnote MCP dans Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"footnote": {
"command": "npx",
"args": [
"-y",
"@brick-byte/footnote"
],
"env": {
"DATABASE_URL": "<YOUR_DATABASE_URL>"
}
}
}
}Installer footnote MCP dans VS Code
.vscode/mcp.json
{
"servers": {
"footnote": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@brick-byte/footnote"
],
"env": {
"DATABASE_URL": "<YOUR_DATABASE_URL>"
}
}
}
}Installer footnote MCP dans VS Code CLI
$ code --add-mcp '{"name":"footnote","type":"stdio","command":"npx","args":["-y","@brick-byte/footnote"],"env":{"DATABASE_URL":"<YOUR_DATABASE_URL>"}}'Installer footnote MCP dans Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"footnote": {
"command": "npx",
"args": [
"-y",
"@brick-byte/footnote"
],
"env": {
"DATABASE_URL": "<YOUR_DATABASE_URL>"
}
}
}
}Installer footnote MCP dans Codex
$ codex mcp add footnote --env 'DATABASE_URL=<YOUR_DATABASE_URL>' -- npx -y @brick-byte/footnoteInstaller footnote MCP dans Codex config.toml
~/.codex/config.toml
[mcp_servers.footnote] command = "npx" args = ["-y", "@brick-byte/footnote"] [mcp_servers.footnote.env] DATABASE_URL = "<YOUR_DATABASE_URL>"
Installer footnote MCP dans Gemini CLI
$ gemini mcp add -s user -e 'DATABASE_URL=<YOUR_DATABASE_URL>' footnote npx -- -y @brick-byte/footnoteInstaller footnote MCP dans Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"footnote": {
"command": "npx",
"args": [
"-y",
"@brick-byte/footnote"
],
"env": {
"DATABASE_URL": "<YOUR_DATABASE_URL>"
}
}
}
}Configuration
DATABASE_URLSecretPostgres connection string. Omit to use the built-in SQLite sample database.
PROVENANCE_ACTORIdentity recorded against each provenance record. In production this comes from the request's auth.
PROVENANCE_DBPath to the SQLite provenance log. Defaults to in-memory, which discards the trail on exit.
| Nom | Description | Type |
|---|---|---|
| DATABASE_URL | Postgres connection string. Omit to use the built-in SQLite sample database. | Secret |
| PROVENANCE_ACTOR | Identity recorded against each provenance record. In production this comes from the request's auth. | |
| PROVENANCE_DB | Path to the SQLite provenance log. Defaults to in-memory, which discards the trail on exit. |
Vérifications automatisées
Exécuté le 14 nov. 2026Rapport complet →A passé nos vérifications automatisées. Il ne s'agit pas d'un audit de sécurité : lisez le code et donnez au serveur l'accès le plus restreint dont il a besoin. Fonctionnement des vérifications
- Dépôt source lié et accessiblebrick-byte/footnote is public and reachablegithub.com/brick-byte/footnote ↗Réussi
- Le nom du package correspond au dépôt source@brick-byte/footnote names brick-byte/footnote as sourcenpmjs.com/package/@brick-byte/footnote ↗Réussi
- Provenance du build (attestation Sigstore)No build attestation published for this releaseNon vérifié
- Licence open source (OSI)MITspdx.org/licenses/MIT.html ↗Réussi
- Commit ou version publiée au cours de l'année écouléeLast commit or release 2026-11-05github.com/brick-byte/footnote ↗Réussi
- OpenSSF ScorecardNon vérifié
- Nom du package non proche d'un package populaireNo popular package one edit away from @brick-byte/footnoteRéussi
- Aucun avis critique dans le package ou ses dépendances113 resolved dependencies checked; no critical advisoryosv.dev ↗Réussi
- Aucune instruction cachée destinée au modèle0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersRéussi
- Les outils destructifs sont étiquetésNon vérifié
- Le point de terminaison distant répond à la poignée de main MCPNon vérifié
README
Voir sur GitHubFootnote
An MCP server that prevents hallucinated numbers when AI answers questions over ERP and finance data. Every figure in an answer traces back to the database rows that produced it: clickable at read time, exportable for an auditor, and tamper-evident.
Works with any MCP client: Claude Desktop, Cursor, Microsoft Agent Framework, Semantic Kernel (.NET), LangChain, or your own loop.
An MCP server, a provenance store, and a demo UI showing what the combination looks like.
The quickest way to try it:
// claude_desktop_config.json — sample data, nothing to install
{ "mcpServers": {
"footnote": {
"command": "npx",
"args": ["-y", "@brick-byte/footnote"],
"env": { "PROVENANCE_ACTOR": "your-name" }
} } }
Against your own database it reads from two, never one — the ERP read-only, the audit trail somewhere you own. Run footnote check first; see Connecting to an existing database.
{ "mcpServers": {
"footnote": {
"command": "npx",
"args": ["-y", "@brick-byte/footnote"],
"env": {
// Read-only role. Footnote never writes here and never migrates it.
"DATABASE_URL": "postgres://footnote_ro:pass@host:5432/erp",
// The append-only provenance log, deliberately a separate database.
"PROVENANCE_DB": "/path/to/footnote-provenance.db",
"PROVENANCE_ACTOR": "your-name"
}
} } }
Or run the demo UI locally:
npm install
npm run demo # http://localhost:4711
npm test # 30 tests, including the invariants below
Node 22.5+ required (uses the built-in node:sqlite, so there is no database to install).
Postgres is opt-in. The same schema, seed and query set run against it, and the same suite has to pass on both:
npm run db:up # Postgres 17 in Docker, seeded from migrations/001_init.sql
npm run test:pg # the same suite + 2 Postgres-only checks (32)
npm run demo:pg # the demo, against Postgres

The problem
Language models produce plausible continuations, not true ones. Point one at a business database and it will confidently report a number that no query produced — and the fabricated figure is indistinguishable from the real one, because both come out of the same machinery.
The usual answers don't hold up here. Uncertainty signals catch the fuzzy cases, not the fluent ones. A verifier built from the same model can confirm a fabrication as easily as catch it. And in finance, inventory or procurement, "the model said so" is not an answer anyone can act on.
What does work is structural: never let the model produce the number.
The architecture
question
│
▼
model ──────────► picks an operation from a catalog and supplies typed args
│ (it cannot write SQL, cannot invent an operation)
▼
contract layer ─► validates params, resolves entities against the database,
│ rejects anything that does not exist
▼
deterministic ──► executes the query; SQL does all aggregation
core returns values + the evidence behind each one
│
▼
provenance ─────► appends a hash-chained record, server-side,
store where the model cannot influence it
│
▼
host UI ────────► fills slots from structured output and renders each
claim as a clickable citation
The model handles translation and phrasing — the two things it is reliable at. Numbers come from the system of record.
What it enforces
These are tests, not guidelines. npm test fails if any of them breaks.
No number is generated. Values are copied verbatim from an operation's structured output into template slots. A test asserts every monetary figure in an answer is covered by a claim with evidence behind it, and that the stated total equals the sum of the records it cites.
Entities are validated before any query runs. A fabricated customer produces a recoverable error listing real alternatives — not a silent empty result the model narrates around.
Aggregation happens in SQL. The model chooses which aggregation to run, never what it equals.
Empty results are handled in code. This is the single biggest fabrication trigger: hand a model an empty result set mid-sentence and it invents something to finish the sentence. Operations set an explicit emptyReason instead.
Unroutable questions are refused. "What will revenue be next quarter?" maps to no operation, so no answer is produced. Refusal is a first-class outcome, not a failure.
Provenance is written server-side. The model never reports its own provenance. Provenance that depends on the model choosing to cite is worthless.
The log is tamper-evident. Each record carries the hash of its predecessor. npm run verify walks the chain and reports the first record that was modified after it was written.
Query ordering is a tested contract. listCustomers must return record order, because entity extraction takes the first match. Sorting it by name instead produces the failure this project exists to prevent: a fluent sentence, a real figure, correctly cited to real rows, about the wrong company. There is a test for exactly that.
Interpretations, not just figures
The harder case is judgement. "Bergmann is at risk" is a conclusion with no row to check it against — and an ungrounded interpretation is more dangerous than an ungrounded number, because it reads as insight and survives review.
The answer here states the conclusion and then lays out each premise as a separately cited fact:
Bergmann Logistik GmbH shows two independent risk signals.
This is an interpretation — the underlying facts are:
· 43.805,00 € overdue across 4 invoices, oldest 104 days past due
· 2 open support tickets, 1 high severity
· agreed payment terms of 30 days, account owned by Ana Kovač
The conclusion is the model's. Every fact above is a record you can open.
A human can disagree with the reasoning while trusting the inputs.
Provenance record format
{
"id": "…", "sequence": 1, "timestamp": "2026-08-14T09:12:04.000Z",
"actor": { "id": "zoran", "role": "controller" },
"question": "How much does Bergmann owe?",
"answer": "Bergmann Logistik GmbH is 43.805,00 € overdue across 4 invoices…",
// Each claim indexes a span of the answer and names its evidence.
"claims": [
{
"text": "43.805,00 €",
"span": { "start": 25, "end": 36 },
"evidenceIds": ["invoice:8812", "invoice:8834", "invoice:8901", "invoice:8977"],
"origin": "structured" // never "generated" for a value
}
],
// The query, so the result is reproducible.
"operations": [
{ "name": "getOverdueInvoices",
"arguments": { "customer": "Bergmann", "asOfDate": "2026-08-14" },
"query": { "sql": "SELECT …", "params": ["2026-08-14", 4471, "2026-08-14"] },
"durationMs": 0.42 }
],
// Field values, not just IDs — the export stands alone if the source moves on.
"evidence": [
{ "id": "invoice:8812", "type": "invoice", "recordId": "8812",
"uri": "erp://invoice/8812",
"fields": { "number": "INV-2026-8812", "due_on": "2026-05-02",
"outstanding": "18.450,00 €", "days_overdue": 104 } }
],
"previousHash": "0000…", "hash": "9aa2ba…"
}
origin is the field that matters. structured means the value was copied from an operation's output. generated means a model produced it — which for a number is exactly what this project exists to prevent.
MCP details
The server uses the parts of the protocol that carry this work:
| Feature | Use |
|---|---|
inputSchema |
The model gets a typed catalog, not a query language |
structuredContent |
Values return as validated JSON beside the prose, so figures never have to survive a round trip through generated tokens |
resource_link |
Every record touched comes back as an erp:// URI — the deep-link primitive behind a clickable citation |
annotations.audience |
Record links are marked user-facing |
_meta |
Carries the provenance record ID and hash so a host can fetch the full trace |
isError |
A fabricated entity is a recoverable tool error the model can correct, not a protocol failure |
What MCP does not give you, and what this repo adds: nothing in the protocol binds this claim to that evidence. The protocol hands you links; the claim-to-evidence mapping and its rendering live in the host. That binding is the actual product.
Run standalone over stdio:
npm run mcp
The claude_desktop_config.json entry is at the top of this README.
Running from source (for development)
{ "mcpServers": {
"footnote": {
"command": "npx",
"args": ["tsx", "--experimental-sqlite", "/path/to/footnote/src/mcp-server.ts"],
"env": { "PROVENANCE_DB": "/path/to/provenance.db", "PROVENANCE_ACTOR": "your-name" }
} } }
Connecting to an existing database
By default Footnote runs against its own throwaway sample database. Set DATABASE_URL and it switches to external mode, meant for a database it did not create — a customer's ERP.
External mode changes three things, all of them about not damaging a system that isn't ours:
- The migration never runs. In demo mode Footnote creates and seeds
customers,invoices,paymentsandtickets. Against a real database that would either crash on a read-only role or, worse, succeed — inserting fabricated invoices into a live finance system.FOOTNOTE_SEED=1is the only way to opt back in, and exists for our own Docker Postgres. - The ERP connection is read-only at the session level. Every pool connection starts with
default_transaction_read_only=onand astatement_timeout. The catalog only ever emitsSELECT, but that is a property of code someone can change; this is enforced by the server. - The provenance log goes somewhere else. It is append-only and needs write access, so it never shares the ERP connection. Writing an audit trail into the database being audited would mean asking for write access to the very system under audit.
Create a read-only role
CREATE ROLE footnote_ro LOGIN PASSWORD '…';
GRANT CONNECT ON DATABASE your_erp TO footnote_ro;
GRANT USAGE ON SCHEMA public TO footnote_ro;
GRANT SELECT ON ALL TABLES IN SCHEMA public TO footnote_ro;
-- Postgres 15+ already revokes this from PUBLIC; older versions do not.
REVOKE CREATE ON SCHEMA public FROM footnote_ro, PUBLIC;
-- So tables added later are readable too, without re-granting by hand.
ALTER DEFAULT PRIVILEGES IN SCHEMA public GRANT SELECT ON TABLES TO footnote_ro;
Environment variables
| Variable | Default | Purpose |
|---|---|---|
DATABASE_URL |
unset | The ERP. Setting it enables external mode. Unset means demo mode. |
PROVENANCE_DATABASE_URL |
unset | Postgres for the provenance log. Never falls back to DATABASE_URL. |
PROVENANCE_DB |
./footnote-provenance.db in external mode, :memory: in demo |
SQLite path for the provenance log, when PROVENANCE_DATABASE_URL is unset. |
FOOTNOTE_SEED |
unset | 1 applies the demo schema and seed. Never set this against a customer database. It also makes the ERP connection writable, because seeding writes. |
FOOTNOTE_STATEMENT_TIMEOUT_MS |
5000 |
Statement timeout on the ERP connection. |
PROVENANCE_ACTOR / PROVENANCE_ROLE |
mcp-client / unknown |
Identity recorded against each provenance record. |
Check before you connect
DATABASE_URL=postgres://footnote_ro:…@host:5432/erp npm run check
or, from the installed package, footnote check. It reports the server version, whether those credentials can write, what they can read, which catalog tables and columns are missing, and whether the provenance store opens with an intact chain. It exits non-zero on a finding, so it works as a deployment gate.
The write probe deliberately connects without the read-only session flag — probing through our own default_transaction_read_only=on would have the server reject the write every time and report a pass against a role with full write access. It creates a table inside a transaction that is always rolled back, then verifies nothing was left behind.
Expose your data as views
The catalog reads fixed table and column names and never guesses at mappings. If your schema differs — and it will — create views rather than renaming anything:
CREATE VIEW invoices AS
SELECT ar_doc_id AS id,
doc_number AS number,
bp_id AS customer_id,
doc_date::text AS issued_on,
net_due_date::text AS due_on,
curr AS currency,
ROUND(gross_amt * 100)::bigint AS amount_cents,
ROUND(paid_amt * 100)::bigint AS paid_cents,
CASE WHEN clearing_date IS NOT NULL THEN 'paid' ELSE 'open' END AS status
FROM fi_open_items;
Two things that will bite otherwise: dates must come back as text in YYYY-MM-DD, because a driver-returned Date object renders as Tue May 02 2026 … inside claim text and breaks the span offsets that make citations clickable; and money must be integer cents, never floats. npm run check lists exactly which columns are missing.
What you get over plain MCP, and what needs host integration
Any MCP client — Claude Desktop, Microsoft Agent Framework, Semantic Kernel, LangChain, your own loop — can call this server today. What that gives you:
- a fixed catalog of typed operations; the model cannot write SQL or invent one
- entity validation, so a fabricated customer is an error rather than an empty result
- aggregation in SQL, never in the model
- refusals instead of improvisation when a question maps to no operation
resource_linkentries identifying every record touched- a hash-chained, server-side provenance log of every call
What it does NOT give you: clickable claim-level citations. Over plain MCP the framework receives structuredContent and resource links, and then its own model composes the answer — at which point the binding between a specific claim and its evidence is gone, and the numbers pass back through generated tokens.
Preserving that binding is host-side work, because nothing in the protocol carries it. src/web.ts and src/public/index.html are the reference implementation: claim spans, citation chips, record resolution. Roughly 200 lines. Port that to your host and you get the other half.
Try these in the demo
| Question | What it shows |
|---|---|
| How much does Bergmann owe? | Every figure clickable to the invoice behind it |
| Is Bergmann Logistik at risk? | An interpretation with separately cited premises |
| Show me the receivables aging | Portfolio aggregation, computed in SQL |
| How much does Acme Corporation owe? | Fabricated entity → refusal with real alternatives |
| What will revenue be next quarter? | Unroutable → refusal rather than improvisation |
Toggle "show what this looks like when the model produces the numbers itself" for the contrast: identical formatting, fluent prose, every figure wrong, nothing in the output marking which.
Layout
migrations/001_init.sql schema + seed, shared by both backends and Docker
src/database.ts the Db seam — SqliteDb and PostgresDb behind one interface
src/db.ts opens the ERP database, applies the migration
src/operations.ts the catalog — the model's entire callable surface
src/compose.ts slot-filling; claims and spans are emitted here
src/provenance.ts append-only hash-chained store, export, verification
src/mcp-server.ts MCP server over stdio
src/web.ts demo host application
src/verify.ts npm run verify / npm run export
src/check.ts npm run check — pre-flight against a customer database
test/run.ts 30 tests covering the invariants above (32 on Postgres)
docker-compose.yml Postgres 17, seeded from the same migration
Only operations.ts writes ERP SQL, in one dialect, with ? placeholders.
PostgresDb rewrites those to $1..$n, and the single expression that genuinely
differs between the engines — whole days between two dates, julianday() on
SQLite, date subtraction on Postgres — is named daysBetween on the Db
interface rather than inlined. That is the one place a port can silently change
a number, so it is isolated and the suite asserts the same day counts on both.
Status and limits
v0, and honest about scope.
- You cannot add provenance to someone else's AI. If the answer comes from SAP Joule or Dynamics Copilot, you have no access to their retrieval pipeline or rendering. This approach applies to AI layers you build yourself over business data.
- Vendor citations exist but stop short. As of August 2026, SAP, Microsoft, NetSuite and Salesforce all ship citations that resolve to knowledge content — help articles, PDFs, documentation. None ships a general mechanism binding a figure to the transaction behind it. Numeric answers are the weakest link everywhere.
- The demo's intent routing is deliberately naive keyword matching, so the project runs with no API key. In a real deployment the model emits the tool call and this code still fills the slots. The architecture is the point, not the routing.
- Writes are out of scope. In an ERP a fabricated read is embarrassing; a fabricated write corrupts a ledger. Writes belong behind a proposal → validation → confirmation flow.
- Retention, access control, and a real deep-link resolver for a specific ERP are the last mile — and the last mile is where the actual product lives.
Prior art worth knowing
- OpenTelemetry GenAI semantic conventions — spans for GenAI clients and MCP. Early; stops well above record-level provenance.
- OpenLineage — dataset and job lineage. Same idea one layer down, for tables rather than claims.
- LLM observability — Langfuse, LangSmith, Arize, Datadog. Tracing for engineers debugging apps, not provenance for the person reading the answer.
License
MIT.
Questions sur footnote MCP
Comment ajouter footnote MCP à Claude Code ?
Exécutez claude mcp add --env 'DATABASE_URL=<YOUR_DATABASE_URL>' footnote -- npx -y @brick-byte/footnote dans votre terminal. Ajoutez --scope user pour le rendre disponible dans tous les projets.
Comment ajouter footnote MCP à Cursor ?
Ouvrez ~/.cursor/mcp.json et ajoutez le serveur sous mcpServers, avec la configuration Cursor indiquée dans la section d'installation ci-dessus.
Comment footnote empêche-t-il les hallucinations ?
Il garantit que le modèle ne génère jamais de chiffres lui-même ; au lieu de cela, les valeurs sont copiées textuellement des sorties de base de données structurées vers des emplacements de modèles prédéfinis.
Le serveur peut-il modifier ma base de données ERP existante ?
Non, le serveur utilise un rôle en lecture seule au niveau de la session et impose un timeout de requête pour garantir qu'il n'écrit jamais sur votre système et ne l'endommage pas.
Où est stocké la piste d'audit ?
Le journal de provenance est stocké dans une base de données séparée en mode append-only pour garantir que la piste d'audit est découplée du système audité.
Le journal de provenance est-il sécurisé ?
Oui, le journal est infalsifiable car chaque enregistrement contient un hash de l'enregistrement précédent.