What can you do with this server?

The tenderapi-mcp server provides tools for AI agents to access and analyze public procurement data from French (BOAMP) and European (TED) sources. * search_tenders: Search public procurement notices with filters including CPV code, region, budget range, deadline, source (BOAMP/TED), status, buyer SIRET, and country. * get_tender: Retrieve details of a specific tender by ID. * search_awards: Find award notices (who won which contracts and for how much), filterable by CPV, region, winner name/SIRET, award date, and amount. (Requires Starter tier) * get_award: Retrieve details of a specific award by ID. (Requires Starter tier) * winner_intel: Aggregated statistics on top-winning companies by contract count and total amount, filtered by CPV, region, and year — useful for competitive intelligence. (Requires Pro tier) * me: Check the current API key's tier, remaining quota, and available features. * Webhook profiles (list_profiles, get_profile, create_profile, update_profile, delete_profile): Manage alert profiles for new tender matches. (Requires Starter tier) * upgrade_tier / billing_portal: Access Stripe checkout and billing management links. Data coverage: BOAMP since March 2015; TED for FR/DE/IT/ES/UK since 2015, refreshed daily. Tiered access: Free (100 req/day, tenders only), Starter (1,000 req/day, adds awards & webhooks), Pro (3,000 req/day, adds winner intel).

How do I use tenderapi-mcp?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@tenderapi-mcp search tenders for IT services in Île-de-France" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

tenderapi-mcp

by IDNSIDNS

Overview Schema Related Servers Score Discussions

Python

Remote

TenderAPI MCP server

Expose TenderAPI (French BOAMP + EU TED public procurement data) as MCP tools for AI agents (Claude Desktop, Cursor, Continue, Zed, etc.).

A thin wrapper over the public REST API at https://tenderapi.fr.

Coverage: BOAMP (France) since March 2015, and TED for FR/DE/IT/ES/UK since 2015 (legacy XML format until end 2023, then eForms), refreshed daily.

Two ways to use it

1. Hosted server — no install, no key

The fastest way to try it. Point any MCP client at the hosted endpoint:

https://tenderapi.fr/mcp

Claude Desktop / Claude Code:

{
  "mcpServers": {
    "tenderapi": {
      "type": "streamable-http",
      "url": "https://tenderapi.fr/mcp"
    }
  }
}

Exposes search_tenders and get_tender. Anonymous, free, limited to 30 tool calls per day per IP. No account, nothing to install.

Awards, winner intelligence and alert profiles are not available anonymously — they need a key, see below.

2. Local server (pip) — full toolset

Requires Python 3.10+ and a free API key.

pip install tenderapi-mcp

Get a free key at https://tenderapi.fr/ (100 requests/day), then:

{
  "mcpServers": {
    "tenderapi": {
      "command": "tenderapi-mcp",
      "env": {
        "TENDERAPI_KEY": "ta_your_key_here"
      }
    }
  }
}

Claude Desktop config location:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json

Restart the client. The tenderapi server should appear in the tool picker.

From source instead of PyPI:

git clone https://github.com/IDNSIDNS/tenderapi-mcp
cd tenderapi-mcp
pip install -e .

Any MCP client supporting stdio transport works. The tenderapi-mcp binary installed by pip is the entry point.

Related MCP server: mcp-south-africa-tenders

Tools exposed

Tool	Tier	Hosted (keyless)	Description
`search_tenders`	Free	✅	Search BOAMP + TED tenders with typed filters (CPV, region, budget, deadline, source, etc.)
`get_tender`	Free	✅	Fetch a single tender by id
`search_awards`	Starter	—	Search award notices (who won which contract, for how much)
`get_award`	Starter	—	Fetch a single award by id
`winner_intel`	Pro	—	Aggregated winner stats: top companies by CPV / region / year
`me`	any	—	Current key tier, quota remaining, available features
`list_profiles`, `get_profile`, `create_profile`, `update_profile`, `delete_profile`	Starter	—	Manage alert profiles (daily email digest, Teams card, or webhook) for new-tender matches
`upgrade_tier`, `billing_portal`	any	—	Stripe checkout and billing-management links

PINs (prior-information notices) are excluded from search_tenders by default; pass include_planning=true to include them. A deadline_after/deadline_before filter drops notices with no submission deadline unless include_null_deadline=true.

Tiers

Hosted, keyless: 30 tool calls/day per IP, tenders only
Free key: 100 req/day, tenders only
Starter (5 €/month): 500 req/day, adds awards + alert profiles (email digest, Teams or webhook)
Pro (15 €/month): 1 500 req/day, adds winner intelligence

Prices are final — no VAT is charged (art. 293 B French tax code). See https://tenderapi.fr/#pricing.

Local development

Override the API base URL via TENDERAPI_BASE_URL (default https://tenderapi.fr).

Requirements

Pinned to the mcp 1.x line: version 2.0.0 removed mcp.server.fastmcp, which this server is built on. Migration to the 2.x API is tracked separately.

License

MIT, see LICENSE.

Available Tools

4 tools

meAInspect

Return the authenticated key's tier, quota remaining, and available features.

Useful for the agent to check quota before launching many calls or to pick a tier-appropriate strategy.

ParametersJSON Schema

Name	Required	Description	Default
No parameters

Output Schema

ParametersJSON Schema

Name	Required	Description
No output parameters

TDQS

A4.7/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Despite no annotations, the description discloses the return values and implies a read-only operation. Could mention authentication failure behavior but is adequate.

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?

Two concise sentences front-load the purpose and add usage guidance without waste.

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?

With zero parameters and an output schema, the description fully covers what the tool does and when to use it.

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?

No parameters exist, so baseline 4 applies. Description adds no parameter info, which 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 clearly states the tool returns the authenticated key's tier, quota remaining, and available features, distinguishing it from sibling tools like search_awards.

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?

Explicitly advises using it to check quota before launching many calls or to pick a tier-appropriate strategy, providing clear use context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

search_awardsAInspect

Search award notices — who won which public contract, for how much.

Requires Starter tier or above.

Args: cpv: CPV code filter. region: Region slug. winner_name: Partial match on the winning company name. winner_siret: Exact SIRET match (14 digits). awarded_after: ISO date; awards with an award date after this. amount_min: Minimum contract amount, EUR. source: "boamp" or "ted". page / page_size: Pagination.

ParametersJSON Schema

Name	Required	Description	Default
`cpv`	No
`region`	No
`winner_name`	No
`winner_siret`	No
`awarded_after`	No
`amount_min`	No
`source`	No
`page`	No
`page_size`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
No output parameters

TDQS

A3.5/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden. It indicates a read-only search but does not disclose error handling, rate limits, or any behavioral nuances beyond parameter descriptions.

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 efficiently structured: a clear one-sentence purpose, a requirement line, and a bulleted parameter list. No wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers purpose and parameter semantics but lacks examples, error scenarios, or explicit behavioral details. An existing output schema reduces the need to describe return values, but the description could be more thorough for a 9-parameter tool.

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?

The description provides brief one-liners for each of the 9 parameters (e.g., 'cpv: CPV code filter'), adding meaning beyond the schema's titles and types. However, it lacks details like formats or allowed values, and schema coverage is 0%.

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 clearly states it searches for award notices (who won which public contract, for how much), distinguishing it from sibling tools like search_tenders (tenders) and winner_intel (likely winner intelligence).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description mentions a prerequisite (Starter tier or above) but does not explicitly guide when to use this tool vs. alternatives or exclude cases. Usage is implied but not fully delineated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

search_tendersAInspect

Search public procurement tenders from BOAMP (France) and TED (EU).

Returns a paginated list of tender notices matching the filters.

Args: cpv: CPV classification code (e.g. "72000000" for IT services). region: French region slug, lowercase (e.g. "occitanie", "ile-de-france", "bretagne"). budget_min: Minimum estimated budget, EUR. budget_max: Maximum estimated budget, EUR. deadline_after: ISO date (YYYY-MM-DD); only tenders with submission deadline after this date. source: "boamp" (France) or "ted" (EU-wide). Omit to include both. status: "open" | "closed" | "awarded". buyer_siret: Exact SIRET of the French contracting authority (14 digits). country: ISO 3-letter country code (default FR). page: 1-indexed page number. page_size: Results per page, 1-100.

Returns a dict with keys: total, page, page_size, results (list of tenders).

ParametersJSON Schema

Name	Required	Description	Default
`cpv`	No
`region`	No
`budget_min`	No
`budget_max`	No
`deadline_after`	No
`source`	No
`status`	No
`buyer_siret`	No
`country`	No
`page`	No
`page_size`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
No output parameters

TDQS

A4.1/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full burden. It explains the paginated return format and non-destructive nature implicitly, but does not disclose rate limits, authentication requirements, or other behavioral constraints, meeting only minimal adequacy.

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 concisely structured with a brief introductory line, followed by a clear bullet-point list of parameters and a final line about the return value. Every sentence adds value, with no repetition or fluff.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 11 parameters, no annotations, and an output schema, the description adequately covers the input semantics and return structure. However, it lacks examples, error handling, or edge-case behavior, which would make it fully complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description must compensate. It provides detailed, human-readable explanations for all 11 parameters (e.g., 'CPV classification code (e.g. "72000000" for IT services)'), adding significant meaning beyond the schema's type and name information.

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 clearly states the tool searches for public procurement tenders from specific sources (BOAMP and TED). It uses a specific verb 'search' and resource 'tenders', distinguishing it from sibling tools like 'search_awards' and 'winner_intel'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides parameter details but no explicit guidance on when to use this tool versus alternatives like search_awards or winner_intel. It does not mention conditions, prerequisites, or exclusions, leaving usage inference implied.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

winner_intelAInspect

Aggregated winner statistics — top companies by contract count and total amount.

Requires Pro tier. Use for competitive intelligence: "which companies win IT contracts in Occitanie in 2025?".

Args: cpv: CPV code filter. region: Region slug. year: Integer year filter (e.g. 2025). limit: Top N results (default 10, max 50).

ParametersJSON Schema

Name	Required	Description	Default
`cpv`	No
`region`	No
`year`	No
`limit`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
No output parameters

TDQS

A4.2/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description carries full burden. States Pro tier requirement (authorization). Does not mention rate limits, response size, or mutation behavior, but it is clearly a read-only aggregation. Output schema covers return format, so that is acceptable.

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?

Two sentences in first paragraph plus a bulleted arg list. No fluff, front-loaded with core purpose, then usage condition, example, and parameters.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool is simple; description covers purpose, parameters, and authorization. Output schema handles return values. Adequate for an aggregation tool with few parameters.

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?

Schema coverage is 0%, but description adds explanations for all four parameters (cpv, region, year, limit) including default and max for limit. This adds value beyond the schema's type/default fields.

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?

Clearly states it provides aggregated winner statistics (top companies by contract count and total amount). The example query 'which companies win IT contracts in Occitanie in 2025?' makes purpose immediately understandable. Distinguishes from siblings (search_awards, search_tenders) by being an aggregation tool rather than a search tool.

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?

Mentions 'Requires Pro tier' (precondition) and gives a usage example. Does not explicitly contrast with siblings, but the nature of the tool (aggregated statistics vs. individual searches) is implied.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

4 tool updatesv0.1.2May 30, 2026
- First observedme
- First observedsearch_awards
- First observedsearch_tenders
- First observedwinner_intel

Install Server

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A3.9/5.0

Disambiguation5/5

Each tool has a clearly distinct purpose: 'me' for account info, 'search_awards' for award notices, 'search_tenders' for procurement tenders, and 'winner_intel' for aggregated winner statistics. No overlap exists, making it easy for an agent to select the correct tool.

Naming Consistency2/5

Tool names are inconsistent: 'me' is a single word without a verb, while 'search_awards' and 'search_tenders' follow a verb_noun pattern, and 'winner_intel' is a noun compound. This mixture of conventions (one-word, verb_noun, noun_noun) creates confusion and lacks a predictable pattern.

Tool Count5/5

With only 4 tools, the server is well-scoped for its purpose of querying public procurement data. Each tool addresses a core need (account check, award search, tender search, winner analytics) without unnecessary bloat or missing essentials.

Completeness4/5

The tool set covers the main workflows for procurement data exploration: account info, searching awards and tenders, and winner statistics. However, a tool to retrieve full details of a specific tender or award by ID is missing, which is a minor gap but agents can work around it using search filters.

Maintenance

ActivityMaintained

ResponsivenessSyncing

Resources

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

mcp-ted B
io.github.lexsocket
TED MCP Server: Real-time EU public tenders access. https://www.lexsocket.ai/
Government Data Search Open Data
2
Tender MCP A
io.github.OjasKord
Government tender search for AI agents. UK, EU and US procurement opportunities.
Government Data Search Open Data
22
oro-intel-mcpOAuth
io.github.oro-intel
UK public procurement data for AI agents: tenders, contracts, buyer and supplier profiles.
Government Data Open Data
2
cerebro-mcp
io.github.benjixone
Government tenders, awards and pre-tender pipelines from 21 official sources as MCP tools.
Government Data Open Data
1

Related MCP Servers

mcp-marches-publics
Government Data Open Data
AgentIA1984-cmd
F
license
Not graded
quality
C
maintenance
Provides tools to search and retrieve French public procurement data (tenders, awarded contracts) and company information from official open APIs.
Updated 2 months ago (2026-07-06 11:15 UTC)
-
mcp-south-africa-tenders
Government Data Open Data
pipeworx-io
A
license
Not graded
quality
C
maintenance
Enables AI agents to query South Africa government tender data from National Treasury eTenders via a keyless MCP gateway.
Updated 11 days ago (2026-08-26 17:42 UTC)
16
MIT
chile-procurement
Government Data Open Data
pipeworx-io
A
license
Not graded
quality
C
maintenance
Enables access to Chile's government procurement data (Mercado Público / ChileCompra) via MCP, allowing AI agents to query public procurement information.
Updated 11 days ago (2026-08-26 16:47 UTC)
16
MIT
France Data MCP
Government Data Open Data Real Estate
takatin31
F
license
Not graded
quality
C
maintenance
Provides AI agents with access to French public registries including company records, property sale prices, housing energy performance, and short-term rental rates via MCP tools.
Updated a month ago (2026-08-05 10:29 UTC)
-

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/IDNSIDNS/tenderapi-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server