Skip to main content
Glama

Public Tenders (EU, US, UK, AU)

kadi_bence/sam-gov-scraper

kadi_bence--sam-gov-scraper
Destructive

This tool calls the Actor "kadi_bence/sam-gov-scraper" and retrieves its output results. Actor description: $1.50 per 1,000 notices. Search US federal contract opportunities, RFPs and awards on SAM.gov (no API key). Input: keywords, notice types, NAICS/PSC codes, set-asides, agencies, states, posted dates. Returns per notice: title, agency, NAICS, set-aside, response deadline, place of performance, URL.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "kadi_bence--sam-gov-scraper"
  }
}

Input Schema

NameRequiredDescriptionDefault
apiKeyNoNot needed for active notices. Your own free public API key from SAM.gov (Account Details > Public API Key) unlocks archived notices and attachment links through the official Get Opportunities API. Personal keys allow 10 requests per day (1,000 records each). Stored encrypted, never logged.
agenciesNoWords from the department, agency or office name, e.g. 'Veterans Affairs', 'Navy', 'Army Corps of Engineers', or an abbreviation (DOD, VA, GSA, DHS, NASA, HHS, NIH, USDA...). Several lines = any of them.
keywordsNoSearched in the title, solicitation number and full description. One line = all its words must appear (e.g. 'cloud migration'); put a line in quotes for an exact phrase ("janitorial services"). Several lines = any of them. Leave empty to get every notice that matches the other filters.
postedToNoLast posted date (YYYY-MM-DD).
pscCodesNoe.g. D302 (IT systems development), R425 (engineering support), 7030 (software). Prefixes work: D3 returns all D3xx codes.
waitSecsNoMax seconds (0–45, default 30) to cap the wait for the Actor run to reach terminal state. For long-running Actors the response returns at the cap with the current run status; follow `nextStep` to poll via get-actor-run. Set to 0 to fire-and-forget.
activeOnlyNoArchived (inactive) notices are only available with your own SAM.gov API key (see Advanced). Example values: true
dataSourceNoAuto: the keyless official daily extract of all active notices; the official API (needs your key) only when you ask for archived notices or attachment links. Example values: "auto"auto
maxResultsNoStop after this many opportunities. 0 = no limit (there is no 10,000 cap). The default without input (API, MCP and AI-agent calls) is 20. Example values: 20
naicsCodesNoIndustry codes, e.g. 541511 (custom programming) or 236220 (commercial construction). Prefixes work: 5415 returns every 5415xx code, 23 all construction.
postedFromNoFirst posted date (YYYY-MM-DD).
monitorNameNoKeeps separate 'already seen' lists for different schedules. Example values: "default"default
noticeTypesNoLeave empty for all types. 'Solicitation' and 'Combined synopsis/solicitation' are open bids; 'Award notice' shows who won and for how much. Example values: ["solicitation","combined_synopsis_solicitation"]
setAsideTypesNoSmall-business set-asides. Leave empty for all. 'No set-aside' = full and open competition.
minAwardAmountNoOnly award notices with at least this awarded amount. Leave empty for all notices.
postedWithinDaysNoe.g. 7 for the last week, 1 for yesterday and today. Leave empty to use the date range below (or no date limit). Short windows are also faster. Example values: 7
fetchDescriptionsNoThe official API returns descriptions as separate links: each one costs one request of your key's daily quota. The keyless extract always includes descriptions.
includeAttachmentsNoAdds direct download links to the notice's documents (RFP, SOW, amendments). Uses the official API, so it needs your key.
proxyConfigurationNoNot needed: SAM.gov publishes this data as official open data. Example values: {"useApifyProxy":false}
onlyNewOpportunitiesNoRemember returned notices and output only NEW ones on the next runs with the same search. Ideal for a daily schedule: you only pay for new opportunities.
responseDeadlineAfterNoOnly bids you can still answer: notices whose response deadline is on or after this date (notices without a deadline are left out). Accepts YYYY-MM-DD, 'today' or '+7 days'.
stateFallbackToOfficeNoBroadens the state filter: notices without a place-of-performance state are matched on the state of the buying office.
placeOfPerformanceStatesNo2-letter state codes. Note: only about 1 in 3 notices lists a place-of-performance state; tick the option below to fall back to the contracting office's state.

Output Schema

NameRequiredDescriptionDefault
tipNoAdvisory guidance RAG Web Browser wrote to its key-value store under the reserved "TIP" key
runIdYesActor run ID
statsNoRun statistics
statusYesRun status: READY | RUNNING | TIMING-OUT | TIMED-OUT | ABORTING | ABORTED | SUCCEEDED | FAILED
actorIdYesStable Apify Actor ID from the run record
summaryYesPast-tense summary of the run state
exitCodeNoActor process exit code; populated for terminal states (especially FAILED)
nextStepYesOne primary follow-up action with identifiers interpolated
storagesYesDataset and key-value store metadata, keyed by alias. "default" is always the primary entry.
actorNameNo"username/actor-name"
startedAtNoISO timestamp when the run started
finishedAtNoISO timestamp when the run finished (terminal states only)
statusMessageNoPass-through from Apify run.statusMessage
apifyConsoleUrlNoPersonalized Apify Console link to the run; present only for Console sessions

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedOutput schema / properties / storages / properties / datasets / properties / default / properties / itemsSchema
      Added value: +{
      +  "description": "JSON Schema for rows in the dataset at `storages.datasets.default.id` — describes row shape only; the rows themselves are NOT returned inline in this response. Inferred from this Actor's historical successful runs. To fetch actual rows, call `get-dataset-items` with the dataset id and a `fields` projection drawn from this schema.",
      +  "properties": {
      +    "active": {
      +      "type": "boolean"
      +    },
      +    "additionalInfoLink": {
      +      "type": "null"
      +    },
      +    "agencyCode": {
      +      "type": "string"
      +    },
      +    "archiveDate": {
      +      "type": "string"
      +    },
      +    "attachments": {
      +      "items": {},
      +      "type": "array"
      +    },
      +    "awardAmount": {
      +      "type": "null"
      +    },
      +    "awardDate": {
      +      "type": "null"
      +    },
      +    "awardNumber": {
      +      "type": "null"
      +    },
      +    "awardee": {
      +      "type": "null"
      +    },
      +    "awardeeOmitted": {
      +      "type": "boolean"
      +    },
      +    "baseType": {
      +      "type": "string"
      +    },
      +    "department": {
      +      "type": "string"
      +    },
      +    "description": {
      +      "type": "string"
      +    },
      +    "naicsCode": {
      +      "type": "string"
      +    },
      +    "noticeId": {
      +      "type": "string"
      +    },
      +    "noticeType": {
      +      "type": "string"
      +    },
      +    "noticeTypeCode": {
      +      "type": "string"
      +    },
      +    "office": {
      +      "type": "string"
      +    },
      +    "officeCity": {
      +      "type": "string"
      +    },
      +    "officeCode": {
      +      "type": "string"
      +    },
      +    "officeCountry": {
      +      "type": "string"
      +    },
      +    "officeState": {
      +      "type": "string"
      +    },
      +    "officeZip": {
      +      "type": "string"
      +    },
      +    "placeOfPerformance": {
      +      "type": [
      +        "null",
      +        "string"
      +      ]
      +    },
      +    "placeOfPerformanceCity": {
      +      "type": [
      +        "null",
      +        "string"
      +      ]
      +    },
      +    "placeOfPerformanceCountry": {
      +      "type": [
      +        "null",
      +        "string"
      +      ]
      +    },
      +    "placeOfPerformanceState": {
      +      "type": [
      +        "null",
      +        "string"
      +      ]
      +    },
      +    "placeOfPerformanceZip": {
      +      "type": [
      +        "null",
      +        "string"
      +      ]
      +    },
      +    "postedDate": {
      +      "type": "string"
      +    },
      +    "pscCode": {
      +      "type": "string"
      +    },
      +    "responseDeadline": {
      +      "type": "string"
      +    },
      +    "scrapedAt": {
      +      "type": "string"
      +    },
      +    "setAside": {
      +      "type": [
      +        "null",
      +        "string"
      +      ]
      +    },
      +    "setAsideCode": {
      +      "type": [
      +        "null",
      +        "string"
      +      ]
      +    },
      +    "solicitationNumber": {
      +      "type": "string"
      +    },
      +    "source": {
      +      "type": "string"
      +    },
      +    "subTier": {
      +      "type": "string"
      +    },
      +    "title": {
      +      "type": "string"
      +    },
      +    "url": {
      +      "type": "string"
      +    }
      +  },
      +  "type": "object"
      +}
  2. First observed

TDQS

B3.1/5.0
Behavior3/5

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

The annotations declare readOnlyHint=false and destructiveHint=true, which the description never explains or reconciles with a 'retrieves its output results' framing; an agent has no idea what is being mutated. On the positive side, the description adds genuinely useful context the annotations do not carry: the $1.50 per 1,000 notices cost and the keyless-vs-API data path. The wait/polling behavior (waitSecs, nextStep) is left entirely to the schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

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

Two sentences, front-loaded with the actor invocation and pricing, but the opening clause ('This tool calls the Actor ... and retrieves its output results') is boilerplate that conveys nothing an agent could not guess from the tool name. The useful material — cost, keyless access, return fields — is compressed but present.

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?

An output schema exists, so return-value explanation is not strictly required. But for a 23-parameter tool with nested proxy config, monitoring mode (onlyNewOpportunities/monitorName), and a wait/poll workflow, the description covers only the happy path and omits how runs are polled or how stateful monitoring behaves. Adequate but clearly thin relative to the tool's complexity.

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% across 23 parameters, so the schema already does the heavy lifting. The description's input list (keywords, notice types, NAICS/PSC codes, set-asides, agencies, states, posted dates) merely restates parameter groups without adding syntax or interaction rules. Baseline 3 applies.

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 gives a specific verb and resource: search US federal contract opportunities, RFPs and awards on SAM.gov. It also enumerates the filter inputs and the returned fields, so an agent knows exactly what it gets. It does not, however, distinguish itself from the sibling tender scrapers (gov-tenders, ted-tenders), leaving the regional scoping implicit in the SAM.gov name.

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

Usage Guidelines2/5

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

There is no explicit when-to-use or when-not-to-use guidance and no named alternative. The '(no API key)' note and the archived-notice caveat hint at conditions, but the agent must infer from the schema that an API key is required for archived notices or attachments. Nothing tells it when to pick this over the TED or gov-tenders scrapers.

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.