Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Conceptio Search

PYPI · CONCEPTIO-SEARCH

Search 1M+ open-access papers, standards, and case law from an AI agent.

Available components

−15 this week 70 Trust /100

Last scanned (16 hours ago)

Scores higher than 63% of PyPI servers

Category Education and Research

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security50
  • Malware scan not yet available for this package.Unverified
  • No known CVEs affecting this package version or its production dependencies.Pass
  • Runs setuptools.build_meta at install time, a recognised build step with no custom scripting around it. View diagnostics → Pass
  • 1 of 12 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
Schema Quality & AI Usability76
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 1120 tokens (~124/item across 9 items; 9 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
  • No destabilizing schema changes in the last 30 days.Pass
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • All 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
  • An AI judge read all 10 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a current MCP spec version (2026-07-28).Pass
What we tested

Checks we ran (15)

  • Known CVEs
  • Install scripts
  • Dependency health
  • Source repository
  • Provenance
  • License
  • Maintenance
  • Security disclosure
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Checks we could not complete (1)

These are gaps on our side, not findings about this package. We only credit what we can confirm, so a category made up entirely of them scores 0.

  • Malware scan in Supply Chain SecurityMalware scan not yet available for this package.

Does not apply to this package (2)

  • Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
  • Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 21 Nov 26 +1
    • Stability: 0.97 → pass security
  • 19 Nov 26 −1
    • Stability: pass → 0.93 functional
  • 15 Nov 26 −15
    • Malware scan: pass → unverified ▼ security
  • 14 Nov 26 +15
    • Malware scan: unverified → pass ▲ security
  • 13 Nov 26 −14
    • Malware scan: pass → unverified ▼ security
    • Stability: 0.97 → pass security
  • 12 Nov 26 +15
    • Malware scan: unverified → pass ▲ security
  • 11 Nov 26 −14
    • Malware scan: pass → unverified ▼ security
  • 10 Nov 26 0
    • Security disclosure: unverified → fail ▼ functional
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Nov 2026 · Analysed pypi/conceptio-search@0.3.14

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem pypi
Reason No attestation published

Background: How many MCP packages publish verified provenance →

Install scripts 1 script
Hook Tier Command
build_backend Known build tool setuptools.build_meta

Background: Why install scripts are a supply-chain risk →

Dependencies 12 packages
Packages resolved 12
Stale 1
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 9 exposed · ~1,062 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
conceptio_connectors_send ~96

Save one document to Zotero or open a metadata-only Obsidian handoff. Server-side ownership, connector trial, and failure semantics apply.

NameTypeReqDescription
connectorstringyesTarget connector: 'zotero' saves the document, 'obsidian' opens a metadata-only handoff.
doc_idintegeryesConceptio document ID to save
vaultstring–Optional Obsidian vault name

No output schema declared.

No examples provided.

conceptio_connectors_send_all ~72

Bulk-save selected documents to Zotero. Pro, institutional, or licensed access is required; no free trial path.

NameTypeReqDescription
connectorstring–Target connector — only 'zotero' supports bulk saves.
doc_idsarrayyesConceptio document IDs to save (1-500)

No output schema declared.

No examples provided.

conceptio_download_pdf ~91

Download the original open-access PDF of a paper, standard, or book to a local file path. Accepts a Conceptio document ID (from conceptio_search) or a direct PDF URL.

NameTypeReqDescription
doc_id_or_urlstringyesConceptio document ID (digits) or direct PDF URL
output_pathstringyesLocal destination file path (e.g. 'workspace/paper.pdf')

No output schema declared.

No examples provided.

conceptio_get_citation ~59

Get an academic citation for a document in BibTeX, APA, MLA, or Chicago format.

NameTypeReqDescription
doc_idintegeryesConceptio document ID
formatstring–Citation format to render (default: bibtex).

No output schema declared.

No examples provided.

conceptio_get_document ~45

Fetch complete metadata (title, author, source, license, description, direct PDF URL) for a document ID.

NameTypeReqDescription
doc_idintegeryesConceptio document ID

No output schema declared.

No examples provided.

conceptio_graph_walk ~195

Walk the reference graph from one seed source_id — the compliance walk: what that document cites (direction='out'), what cites it (direction='in'), or both. Optional kind filter selects cites/updates. Returns nodes with a distance from the seed and canonical edges carrying their relation kinds; dangling targets appear as claimed nodes. Metadata-only: spends no credits. Use when an agent needs provenance — what cites this regulation two hops out — instead of a keyword search.

NameTypeReqDescription
directionstring–out = what the seed cites, in = what cites the seed, both = either
hopsinteger–Traversal depth (1 or 2); the server caps the walk here
kindarray–Relation kind(s) to traverse; pass several to intersect them
seedstringyesArchive source_id to start the walk from (e.g. 'usc_42_1396a')

No output schema declared.

No examples provided.

conceptio_resolve ~209

Resolve a known identifier straight to its document(s) in the archive: an RFC number ('RFC 2119'), a DOI ('doi:10.1109/access.2020.2986772'), an arXiv ID ('2604.08499'), a PubMed ID ('PMID 41961061'), a PubMed Central ID ('PMC10601397'), a NIST/FIPS designation ('NIST FIPS 199'), a W3C spec shortname ('w3c_digital-credentials'), or a US legal citation / docket ('347 U.S. 483', '20-5364'). Unrecognized identifiers fall back to a text search. Use this when an agent has a concrete citation/reference it wants to locate precisely.

NameTypeReqDescription
idstringyesThe identifier to resolve (e.g. 'RFC 2119', 'doi:10.x/y', 'PMC10601397')
limitinteger–Max results (1-50)

No output schema declared.

No examples provided.

conceptio_search ~165

Search the open-access archive — papers, technical standards (NIST, OWASP, CISA), textbooks, and legal sources (EUR-Lex, HUDOC) with license-aware access. Requires an API key: run `conceptio auth` once first. Query supports directives like 'source:nist zero trust'.

NameTypeReqDescription
categorystring–Optional category filter: 'Science & Medicine', 'Economics & Finance', 'Computer Science & Tech', 'Social Sciences & Humanities', 'Arts & Culture', 'Law & Regulation'
licensestring–Optional rights filter requiring explicit commercial-use permission.
limitinteger–Number of results (1-20)
querystringyesSearch keywords or directives (e.g. 'source:nist zero trust')

No output schema declared.

No examples provided.

conceptio_search_batch ~130

Run multiple independent searches in one call. Default: queue 1–50 for bounded background execution and return an opaque job handle (poll it with the public API or `conceptio search-job`). Set sync:true to run 1–10 immediately and return all results in one response — each fresh subquery uses one search credit either way.

NameTypeReqDescription
queriesarrayyesSearch objects with q and optional sources, category, language, sort, limit, and offset
syncboolean–Run synchronously (1–10 queries, results in one call) instead of queueing a job

No output schema declared.

No examples provided.

Install

How do I install the Conceptio Search MCP server?

Conceptio Search runs locally as a PyPI package, launched with uvx conceptio-search mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

pypi · conceptio-search

# add to Claude Code
claude mcp add 0x923041-dotcom-conceptio-search -- uvx conceptio-search mcp
Common questions

What is the Conceptio Search MCP server?

Conceptio Search is an MCP server listed in the public MCP registry as io.github.0x923041-dotcom/conceptio-search. Search 1M+ open-access papers, standards, and case law from an AI agent. This page covers its PyPI package (conceptio-search).

Is the Conceptio Search MCP server safe to use?

Conceptio Search scores 70 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 2026. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the Conceptio Search MCP server expose?

Conceptio Search exposes 9 tools: conceptio_search, conceptio_resolve, conceptio_download_pdf, conceptio_get_citation, conceptio_search_batch, and 4 more. Their descriptions and schemas cost roughly 1,062 tokens of context every time the server is loaded.

Is the Conceptio Search MCP server still maintained?

Conceptio Search is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the Conceptio Search MCP server under?

Conceptio Search declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

What did VerifyMCP test on the Conceptio Search MCP server?

VerifyMCP ran 15 checks on Conceptio Search, covering Known CVEs, Install scripts, Dependency health, Source repository and 11 more. One item could not be completed, a gap on our side rather than a finding about Conceptio Search: Malware scan. Endpoint Security and Transport & Reachability do not apply to a PyPI package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.