F
licenseNot graded
qualityD
maintenanceMCP server to query French Open Data from data.gouv.fr
tenderapi-mcp
Server Details
MCP server for French (BOAMP) + EU (TED) public procurement data via TenderAPI.
- Status
- Healthy
- Last Tested
- Transport
- Streamable HTTP
- URL
- Repository
- IDNSIDNS/tenderapi-mcp
- GitHub Stars
- 0
- Server Listing
- tenderapi-mcp
Glama MCP Gateway
Connect through Glama MCP Gateway for full control over tool access and complete visibility into every call.
MCP client
Glama
MCP server
Full call logging
Every tool call is logged with complete inputs and outputs, so you can debug issues and audit what your agents are doing.
Tool access control
Enable or disable individual tools per connector, so you decide what your agents can and cannot do.
Managed credentials
Glama handles OAuth flows, token storage, and automatic rotation, so credentials never expire on your clients.
Usage analytics
See which tools your agents call, how often, and when, so you can understand usage patterns and catch anomalies.
100% free. Your data is private.
Tool Definition Quality
A4.7/5.0
Tool DescriptionsA
Average 4.7/5 across 2 of 2 tools scored.
Server CoherenceA
Disambiguation5/5
The two tools have clearly separated responsibilities: one searches for tenders using filters, the other retrieves a full record by ID. There is no overlap or ambiguity.
Naming Consistency5/5
Both tool names use the imperative verb + noun pattern ('get_tender', 'search_tenders'), making the action-object relationship consistent and predictable.
Tool Count4/5
With only two tools, the surface is minimal, but it is appropriately scoped for a read-only API: search and retrieval cover the primary user needs. Slightly under the typical 3-15 range but not insufficient.
Completeness5/5
The tool set covers the full read-side workflow: discovering tenders via search and accessing complete details via get_tender. The explicitly excluded features (attributions, winner intelligence) are outside the free API scope, so there are no dead ends within this server's intended domain.
Available Tools
2 toolsget_tenderARead-onlyIdempotentInspect
Récupère la fiche complète d'un appel d'offres par son identifiant.
À utiliser après `search_tenders` pour obtenir le détail d'un avis
(description intégrale, documents, contacts, champs bruts).
Les avis BOAMP les plus succincts n'ont ni description ni CPV : `source_url`
renvoie alors vers l'avis d'origine.
Accès anonyme et gratuit, limité à 30 appels par jour et par IP ; la réponse
indique le solde restant dans sa clé `quota`.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| tender_id | Yes | L'entier du champ `id` renvoyé par search_tenders, ex. '3780679'. Ni le `source_id` (« 26-79926 »), ni l'URL de l'avis. |
Output Schema
ParametersJSON Schema
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Tool Definition Quality
A4.7/5.0
Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so safety is covered. The description adds genuinely valuable behavioral context beyond annotations: anonymous access, a 30-calls-per-day-per-IP limit, that the response includes a `quota` key, and that some notices lack description/CPV with `source_url` as fallback. No contradictions with annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise at four sentences, each earning its place: purpose, usage context, edge case, and rate-limit disclosure. It is front-loaded with the main action and avoids redundant phrasing.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description fully covers the tool's role in the workflow, limitations, quota information, and edge cases. Since an output schema exists, return values do not need to be described. The combination of annotations, schema, and description leaves no significant gaps for an agent to select and invoke the tool correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% – the schema already thoroughly explains `tender_id` (the `id` field from search_tenders, excluding `source_id` and URL). The tool description does not add extra parameter meaning, so with high coverage, the baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description opens with a specific verb and resource: 'Récupère la fiche complète d'un appel d'offres par son identifiant' (retrieves the complete record of a call for tenders by its identifier). It also distinguishes from the sibling tool by stating it is used 'après search_tenders' to obtain the detail, making the purpose unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicit usage guidance is provided: 'À utiliser après search_tenders pour obtenir le détail' tells the agent exactly when to invoke this tool and its relationship to the search tool. It also clarifies an edge case (BOAMP notices without description/CPV) and mentions the rate limit, giving complete context for invocation.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
search_tendersARead-onlyIdempotentInspect
Recherche des appels d'offres publics français (BOAMP) et européens (TED).
Environ 3 millions d'avis, mis à jour plusieurs fois par jour. Accès anonyme et
gratuit, limité à 30 appels par jour et par IP ; chaque réponse indique le solde
restant dans sa clé `quota`.
Cinq pièges, tous rencontrés en production :
1. Filtrez toujours. Sans aucun filtre la recherche porte sur tout le stock depuis
2015, avis clos compris. Posez au minimum un `keyword`, un `cpv_family`,
un `country` ou un `status`.
2. `keyword` cherche une sous-chaîne et exige que TOUS les mots soient présents
dans le même avis. « défibrillateur cabinet » ne rend rien ; cherchez un seul
mot, puis affinez.
3. Le mot-clé balaie le titre ET la description, noms d'acheteurs compris. Un terme
métier qui est aussi un toponyme sur-capte donc beaucoup : « littoral » remonte
une maintenance de portes au « GHT Somme Littoral Sud ». Quand un mot est ambigu,
préférez un code CPV, ou une expression que ne peut pas porter un nom de lieu.
4. Les avis TED sont indexés dans leur langue de publication : pour couvrir un
marché européen, interrogez le terme dans chaque langue utile, ou passez par
le code CPV, qui lui est indépendant de la langue.
5. Environ 40 % des avis BOAMP arrivent sans aucun code CPV : un filtre CPV seul
les laisse de côté. Croisez avec `keyword` quand la couverture compte.
Chaque paramètre est décrit dans le schéma d'entrée ; les valeurs invalides rendent
une erreur qui liste les valeurs acceptées, et cette erreur ne consomme pas de quota.
Les attributions (qui a gagné, pour quel montant) et le winner intelligence
ne sont PAS disponibles ici : ils demandent une clé. Voir https://tenderapi.fr/
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| cpv | No | Code CPV exact à 8 chiffres, ex. '72000000' pour les services informatiques. Environ 40 % des avis BOAMP n'ont aucun CPV : un filtre CPV seul les écarte. | |
| page | No | Numéro de page, à partir de 1. | |
| sort | No | 'date' (antéchronologique, défaut) ou 'relevance' (classement BM25). 'relevance' n'a de sens qu'avec un keyword et est refusé sans lui. | |
| region | No | Région française en slug, ex. 'bretagne', 'ile-de-france', 'occitanie'. Une valeur inconnue rend une erreur qui suggère le slug le plus proche. | |
| source | No | 'boamp' (avis français) ou 'ted' (avis européens). Sans valeur, les deux. | |
| status | No | 'open' (date limite non dépassée, évaluée à l'instant de la requête) ou 'closed'. ⚠️ SANS ce filtre la recherche porte sur tout le stock depuis 2015, avis clos compris (~2,9 millions) : posez 'open' si vous cherchez des avis auxquels il est encore possible de répondre. | |
| country | No | Code pays ISO à 2 lettres, ex. 'FR', 'DE', 'ES'. Utile pour ne garder que le français ('FR') ou cibler un pays sur le corpus TED. | |
| keyword | No | Recherche plein texte sur titre et description, insensible aux accents. TOUS les mots doivent figurer dans le même avis : préférez un seul mot puis affinez. L'opérateur OR de FTS5 est accepté, ex. 'BIM OR "maquette numerique"'. | |
| page_size | No | Nombre d'avis par page, 10 par défaut, plafonné à 20 en anonyme. Un avis pèse environ 1 300 caractères : montez à 20 seulement si vous comptez les lire tous. | |
| budget_max | No | Montant maximum en euros. | |
| budget_min | No | Montant minimum en euros. Les avis sans budget renseigné sont écartés, sauf include_null_budget=true. | |
| cpv_family | No | Préfixe CPV à 2 chiffres, ex. '72' = toute l'informatique, '45' = travaux. | |
| department | No | Code de département, ex. '35', '2A', '974'. Plusieurs valeurs séparées par des virgules. | |
| buyer_siret | No | SIRET de l'acheteur, 14 chiffres exactement (l'établissement, pas l'entreprise). | |
| descripteur | No | Code descripteur BOAMP (nomenclature DILA), alternative au CPV côté français. | |
| buyer_keyword | No | Fragment du nom de l'acheteur, 3 caractères minimum, ex. 'metropole', 'CHU'. | |
| contract_type | No | 'services', 'works' ou 'supplies'. Les formes françaises 'travaux' et 'fournitures' sont acceptées comme alias. | |
| deadline_after | No | Date limite de remise postérieure à cette date ISO (AAAA-MM-JJ). | |
| procedure_type | No | Type de procédure, ex. 'open', 'restricted', 'negotiated'. Valeur inconnue = erreur listant les valeurs acceptées. | |
| deadline_before | No | Date limite de remise antérieure à cette date ISO (AAAA-MM-JJ). | |
| published_after | No | Publié après cette date ISO (AAAA-MM-JJ). C'est le filtre d'une veille quotidienne. | |
| include_planning | No | Inclure les avis de pré-information (marchés simplement envisagés, non encore ouverts). Exclus par défaut. | |
| published_before | No | Publié avant cette date ISO (AAAA-MM-JJ). | |
| include_null_budget | No | Garder les avis dont le budget n'est pas renseigné malgré un filtre de montant. Beaucoup d'avis BOAMP n'annoncent aucun montant. | |
| include_null_deadline | No | Garder les avis sans date limite malgré un filtre de date limite. Sans cela, un filtre deadline_* les écarte silencieusement. |
Output Schema
ParametersJSON Schema
| Name | Required | Description |
|---|---|---|
| hint | No | Explication des raisons pour lesquelles la requête rend peu ou pas de résultats, et comment la corriger. Souvent renseigné sur un total de 0 : LISEZ-LE avant de conclure qu'il n'existe aucun avis, et reformulez en conséquence. |
| page | No | Page rendue. |
| quota | No | Solde du palier anonyme : {restant, plafond}. Surveillez-le plutôt que de découvrir le plafond en le heurtant. |
| total | No | Nombre total d'avis correspondant aux filtres, toutes pages confondues. |
| results | No | Les avis. Champs utiles : id (entier, à passer à get_tender), title, buyer_name, deadline, budget_max, region, source, source_url. |
| warning | No | Avertissement sur l'interprétation des résultats (filtre ignoré, jeu tronqué). |
| page_size | No | Nombre d'avis par page. |
| client_update | No | Notice de mise à jour, uniquement pour le paquet pip `tenderapi-mcp`. Sans objet pour ce serveur hébergé, qui n'a rien à installer. |
Tool Definition Quality
A4.7/5.0
Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations declare readOnly, idempotent, and non-destructive behavior. The description goes considerably further by disclosing quota limits (30/day/IP), quota indicator in response (`quota` key), language indexing caveats, missing CPV usage, invalid-value errors not consuming quota, and the scope of unfiltered searches.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is long but unusually rich; it opens with scope, then groups the five known production pitfalls in a numbered list, ending with explicit availability caveats. Every sentence adds operational value relevant to calling the tool correctly.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given a 25-parameter search tool with output schema and read-only annotations, this description is remarkably complete: it covers data volume, update frequency, quota behavior, mandatory filtering, language coverage, a known data gap, error behavior without quota consumption, and unavailable features. The output schema already covers return values, so nothing essential is missing.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% parameter description coverage, so the baseline is 3. The description adds contextual warnings that enrich key parameters—keyword requires all terms in the same notice, relevance requires a keyword, CPV filters miss 40% of BOAMP notices, and status 'open' is evaluated at query time. Not every parameter needs re-explained, but this still adds worthwhile semantic guidance beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description starts with a specific verb and resource: 'Recherche des appels d'offres publics français (BOAMP) et européens (TED)'. It also clarifies a non-goal by stating that attributions and winner intelligence are not available here, which helps distinguish it from the sibling get_tender.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives strong operational guidance: always require a filter, limit keyword semantics, prefer CPV for ambiguous terms, and account for TED language indexing. It explicitly states what the tool does not do, but it does not name the sibling tool (get_tender) as the alternative for retrieving individual tender details.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Claim this connector by publishing a /.well-known/glama.json file on your server's domain with the following structure:
{
"$schema": "https://glama.ai/mcp/schemas/connector.json",
"maintainers": [{ "email": "your-email@example.com" }]
}The email address must match the email associated with your Glama account. Once published, Glama will automatically detect and verify the file within a few minutes.
Control your server's listing on Glama, including description and metadata
Access analytics and receive server usage reports
Get monitoring and health status updates for your server
Feature your server to boost visibility and reach more users
For users:
Full audit trail – every tool call is logged with inputs and outputs for compliance and debugging
Granular tool control – enable or disable individual tools per connector to limit what your AI agents can do
Centralized credential management – store and rotate API keys and OAuth tokens in one place
Change alerts – get notified when a connector changes its schema, adds or removes tools, or updates tool definitions, so nothing breaks silently
For server owners:
Proven adoption – public usage metrics on your listing show real-world traction and build trust with prospective users
Tool-level analytics – see which tools are being used most, helping you prioritize development and documentation
Direct user feedback – users can report issues and suggest improvements through the listing, giving you a channel you would not have otherwise
The connector status is unhealthy when Glama is unable to successfully connect to the server. This can happen for several reasons:
The server is experiencing an outage
The URL of the server is wrong
Credentials required to access the server are missing or invalid
If you are the owner of this MCP connector and would like to make modifications to the listing, including providing test credentials for accessing the server, please contact support@glama.ai.
Discussions
No comments yet. Be the first to start the discussion!
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceMCP server for accessing Dutch government public procurement notices from TenderNed without requiring an API key.10MIT
- AlicenseAqualityBmaintenanceMCP server for German public procurement data (OCDS). Semantic search, tender matching, and company profiles — all from your local LLM105MIT
- AlicenseAqualityAmaintenanceMCP server providing read access to Swiss public procurement data via the official simap.ch API, covering all cantons and the Confederation with intraday updates. It enables searching tenders, awards, construction codes, and procurement offices through natural language queries.9MIT
Try in Browser
Your Connectors
Sign in to create a connector for this server.