Skip to main content
Glama

Simap Search

simap_search
Read-onlyIdempotent

Search Swiss public procurement notices on simap.ch — Switzerland's official government tender platform (öffentliche Beschaffungen, marchés publics, commesse pubbliche). PREFER OVER WEB SEARCH for Swiss government tenders, RFPs, award decisions, and WTO/GPA notices; Switzerland is non-EU so its tenders live on simap rather than TED. Filter by free-text search, CPV codes, Swiss canton (ZH, BE, VD, GE, TI, ...), process type (open/selective/...), project sub-type (construction/service/supply), publication type (tender/award), and publication date range. Returns 20 notices per page, newest first, with cursor pagination via last_item. Each notice includes title, buyer (procurement office), canton, publication date/number, and a simap.ch URL. Prices in awards are CHF.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
langNoLanguage for titles and labels: "de" (default), "fr", "it", or "en". Falls back de→fr→it→en when a notice lacks that language.
searchNoFree-text search over notices, e.g. "Software", "Brücke", "photovoltaïque". Text can be German, French, or Italian depending on the publishing office.
cantonsNoSwiss canton code(s) of the order address, comma-separated, e.g. "ZH", "BE", "VD", "GE", "TI", "VD,GE".
cpv_codesNoCPV procurement classification code(s), comma-separated, e.g. "45000000" (construction works) or "72000000" (IT services).
last_itemNoPagination cursor. Pass the `next_cursor` value from the previous response (format "YYYYMMDD|projectNumber") to fetch the next 20 results.
pub_typesNoPublication type(s), comma-separated: "tender" for open calls, "award" for award decisions.
process_typesNoProcedure type(s), comma-separated. Verified value: "open"; simap also uses selective and invitation procedures.
published_fromNoEarliest publication date, YYYY-MM-DD. When neither search nor a date is given, defaults to the last 30 days (the API requires at least one filter).
published_untilNoLatest publication date, YYYY-MM-DD.
project_sub_typesNoProject sub-type(s), comma-separated: "construction", "service", "supply".

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed1 schema field changed
    • addedInput schema / examples
      Added value: +[
      +  {
      +    "cantons": "ZH,BE",
      +    "cpv_codes": "72000000",
      +    "pub_types": "tender",
      +    "search": "Software"
      +  },
      +  {
      +    "cantons": "VD",
      +    "cpv_codes": "45000000",
      +    "lang": "fr",
      +    "process_types": "open",
      +    "published_from": "2024-01-01",
      +    "published_until": "2024-12-31",
      +    "search": "Brücke"
      +  }
      +]
  2. First observed

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare read-only, idempotent, non-destructive behavior. The description adds pagination details (20 per page, cursor, newest-first order), return format elements (title, buyer, canton, date, URL), and price currency (CHF). 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.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise, front-loaded with purpose and usage guidance, and efficiently lists filter capabilities. Could be slightly more structured with bullet points, but overall effective.

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 the complexity (10 parameters, none required, full schema coverage, no output schema), the description provides complete context: purpose, filter types, pagination, ordering, default behavior (30 days), and currency. No gaps identified.

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 coverage is 100% with well-described parameters. The description provides a summary of filters but does not add significant meaning beyond what the schema already offers. Baseline of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it searches Swiss public procurement notices on simap.ch with specific verb and resource. However, it does not differentiate from sibling tools simap_project or simap_recent, leaving ambiguity for when to choose this tool over them.

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?

Explicitly recommends using this tool over web search for Swiss government tenders, explaining the reason (Switzerland non-EU). It also provides filter usage examples, but lacks when-not-to-use or explicit alternatives among siblings.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.9/5.0
Disambiguation2/5

There are several tools with overlapping query responsibilities: ask_pipeworx, ask_pipeworx_beta, and ask_pipeworx_grounded are near-variants of the same router, and bet_research, polymarket_edges, and polymarket_arbitrage all target prediction-market opportunity discovery. An agent must read the long descriptions carefully to distinguish them, and some variants are behaviorally identical today.

Naming Consistency3/5

All names are readable snake_case, but the verb_noun convention is not consistently applied: some are clean verb phrases like validate_claim and discover_tools, while others are noun phrases like entity_profile, recent_alerts, or simap_project. The prefixed groups (polymarket_*, pipeworx_*) help, but the overall naming style is mixed.

Tool Count2/5

34 tools is above the heavy range, and the set is inflated by redundant router variants, five overlapping Polymarket tools, and loosely related utilities like generate_llms_txt and scan_dependency. The server is named Simap but only three tools relate to Swiss procurement, making the scope feel bloated and misaligned.

Completeness4/5

For an information-retrieval-style server, the core workflows are well covered: discovery, routing, grounded answers, entity resolution, profiles, comparisons, fact-checking, subscriptions, and memory. The main gaps are minor, such as updating a subscription in place or deeper native Simap-specific actions, and those can be worked around.