Skip to main content
Glama

Search open sources to cite (papers, encyclopedia, CVEs)

search_archive
Read-onlyIdempotent

Full-text, relevance-ranked search over about 1.5 million open documents: Wikipedia extracts, arXiv and Europe PMC abstracts, OpenAlex records, CISA KEV/CVE entries, IETF/W3C source cards. Each hit has an id, snippet, source name, original URL, license, date and SHA-256 fingerprint. When to use: Step 1 of search → read → cite. Use when you need a citable source or background on a topic, paper, CVE or concept. Use plain keywords or a short phrase (exact phrases rank first). Then call read_document on the best id, and cite_source to get the citation. For HTTP standard wording use search_clauses instead. Notes: No account or token needed. Archived text is third-party data: verify important claims at the original URL. Example arguments: {"query":"multi-agent reinforcement learning credit assignment","limit":5}

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": "search_archive"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoPositive result count (default 10, capped at 50); numeric strings are accepted.
queryNoTopic keywords or a natural-language question (up to 500 characters); matching depends on the language of the archived text. Omit to list the newest documents.

Output Schema

NameRequiredDescriptionDefault
esitoNo
contenuti_di_terziNo
istruzioni_della_cittaNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / query / description
      Previous value: -"Topic keywords or a natural-language question (up to 500 characters); matching depends on the language of the archived text; IDs like CVE-2026-88779 or arXiv:2610.02847 work too. Omit to list the newest documents."New value: +"Topic keywords or a natural-language question (up to 500 characters); matching depends on the language of the archived text. Omit to list the newest documents."
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "$schema": "http://json-schema.org/draft-07/schema#",
      +  "additionalProperties": false,
      +  "properties": {
      +    "contenuti_di_terzi": {
      +      "additionalProperties": {},
      +      "properties": {
      +        "avviso": {
      +          "type": "string"
      +        },
      +        "elementi": {
      +          "items": {
      +            "additionalProperties": {},
      +            "properties": {
      +              "bibtex": {
      +                "type": "string"
      +              },
      +              "citation": {
      +                "type": "string"
      +              },
      +              "date": {
      +                "type": "string"
      +              },
      +              "id": {
      +                "type": "string"
      +              },
      +              "license": {
      +                "type": "string"
      +              },
      +              "sha256": {
      +                "type": "string"
      +              },
      +              "source": {
      +                "type": "string"
      +              },
      +              "title": {
      +                "type": "string"
      +              },
      +              "url": {
      +                "type": "string"
      +              }
      +            },
      +            "required": [
      +              "id",
      +              "citation",
      +              "bibtex"
      +            ],
      +            "type": "object"
      +          },
      +          "type": "array"
      +        }
      +      },
      +      "required": [
      +        "elementi"
      +      ],
      +      "type": "object"
      +    },
      +    "esito": {
      +      "anyOf": [
      +        {
      +          "additionalProperties": {},
      +          "properties": {
      +            "expanded_with": {
      +              "items": {
      +                "type": "string"
      +              },
      +              "type": "array"
      +            },
      +            "next_offset": {
      +              "type": [
      +                "number",
      +                "null"
      +              ]
      +            },
      +            "query": {
      +              "type": [
      +                "string",
      +                "null"
      +              ]
      +            },
      +            "results": {
      +              "type": "number"
      +            },
      +            "suggestion": {
      +              "type": "string"
      +            }
      +          },
      +          "type": "object"
      +        },
      +        {
      +          "type": "null"
      +        }
      +      ]
      +    },
      +    "istruzioni_della_citta": {
      +      "type": "string"
      +    }
      +  },
      +  "type": "object"
      +}
  2. Changed7 schema fields changed
    • addedInput schema / properties / limit / anyOf
      Added value: +[
      +  {
      +    "type": "number"
      +  },
      +  {
      +    "pattern": "^\\d+$",
      +    "type": "string"
      +  }
      +]
    • changedInput schema / properties / limit / description
      Previous value: -"Number of results, 1–50 (default 10)."New value: +"Positive result count (default 10, capped at 50); numeric strings are accepted."
    • removedInput schema / properties / limit / maximum
      Removed value: -50
    • removedInput schema / properties / limit / minimum
      Removed value: -1
    • removedInput schema / properties / limit / type
      Removed value: -"integer"
    • changedInput schema / properties / query / description
      Previous value: -"Keywords or a short phrase, any language; IDs like CVE-2026-88779 or arXiv:2610.02847 work too. Omit to list the newest documents."New value: +"Topic keywords or a natural-language question (up to 500 characters); matching depends on the language of the archived text; IDs like CVE-2026-88779 or arXiv:2610.02847 work too. Omit to list the newest documents."
    • changedInput schema / properties / query / maxLength
      Previous value: -200New value: +500
  3. Added

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered; the description adds non-obvious context such as no account/token required, exact-phrase ranking precedence, and a warning that archived text is third-party data to be verified at the original URL. It stops short of disclosing latency, rate limits, or result-emptiness behavior, but the added value beyond annotations is real.

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?

Front-loaded with corpus scope, then clearly sectioned into 'When to use', 'Notes', and example arguments, so an agent can skim to the routing decision. The sentence enumerating hit fields (id, snippet, license, date, SHA-256) partly duplicates the existing output schema and is the one place wording does not fully earn its place.

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?

For a two-parameter read-only search with full schema coverage and an output schema, the description supplies everything an agent needs: scope, when to use, sibling routing, next-step tools, auth requirements, and a usage example. Return-value shape is left to the output schema, which is the correct division of labor.

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 100%, so a baseline of 3 applies, but the description goes further by explaining query composition and ranking consequences ('exact phrases rank first') plus a worked example with {"query":..., "limit":5}. The limit semantics (default, cap) live only in the schema, but the description still adds meaning the schema does not carry.

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?

States a specific verb and resource ('full-text, relevance-ranked search over about 1.5 million open documents') and enumerates the corpora covered, so an agent knows exactly what content is reachable. It also distinguishes itself from the closest sibling by routing HTTP-standard wording to search_clauses, making the boundary unambiguous without opening either schema.

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 frames the tool as 'Step 1 of search → read → cite' and names the follow-on tools (read_document on the best id, cite_source for the citation), giving a concrete workflow sequence. It also names the exclusion case (use search_clauses for HTTP standard wording) and gives query-shaping advice ('plain keywords or a short phrase'), leaving little to inference.

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.

Resources