Agent access · experimental

Read the corpus. Know what is live.

The public corpus is available to agents as ordinary machine-readable files today. The hosted MCP server is not live, and the proposed write tools do not accept work. This guide separates the working interfaces from the planned ones.

Open the corpus index → Read the quickstart

Availability

What works right now

Live

Static read access

Corpus index, object JSON, claims graphs, RO-Crates, verification records, content negotiation, and FAIR Signposting.

Planned

Hosted MCP

No remote MCP endpoint exists yet. There is currently no MCP URL to add to Claude, ChatGPT, Codex, or another client.

Unavailable

Write tools

Proposing, verifying, and forking through MCP are design specifications only. Nothing can be submitted through a hosted service.

The source repository includes an MCP contract skeleton, but its data store methods are not implemented. It is useful for inspecting the proposed tool shapes, not for querying the corpus.

Quickstart

Give an agent a reliable path through the corpus

Fetch the corpus index

Start here to discover the available papers and their canonical slugs.
```
curl -L https://datasetpapers.com/papers/index.json
```
Choose a paper and fetch its research object

Replace {slug} with a slug from the index.
```
curl -L https://datasetpapers.com/papers/{slug}/object.json
```
Read the claims and evidence links

The claims graph provides atomic statements, typed relationships, and supporting evidence references.
```
curl -L https://datasetpapers.com/papers/{slug}/claims.json
```
Check independent re-execution

Do this before treating a published number as reliable. A claim's self-reported status is not independent verification.
```
curl -L https://datasetpapers.com/papers/{slug}/verification.json
```

Prompt an agent

A ready-to-use instruction

Paste this into an agent that can fetch public URLs. It keeps discovery and verification in the right order.

Use https://datasetpapers.com/papers/index.json to discover the available analyses.

For the paper you select:
1. Read object.json for the complete research object.
2. Read claims.json for atomic claims and evidence links.
3. Read verification.json before relying on any numerical result.
4. Treat engine-reported verification_status separately from independent re-execution.
5. Cite the paper URL and the specific claim identifier where possible.

This corpus is an experimental prototype, not a product or authoritative source. Report any missing evidence or uncertainty.

Machine surfaces

What each URL gives you

Surface	URL	Use it for
Corpus index	`/papers/index.json`	Discover papers, slugs, identifiers, and top-level metadata.
Research object	`/papers/{slug}/object.json`	Read identifiers, source data, components, claims, gate results, verification, and exports.
Claims graph	`/papers/{slug}/claims.json`	Work with atomic claims and typed evidence, derivation, and containment relationships.
RO-Crate	`/papers/{slug}/ro-crate-metadata.json`	Traverse the packaged research object as JSON-LD.
Verification	`/papers/{slug}/verification.json`	Inspect the independent re-execution environment, inputs, comparisons, and result.
Discovery	`/.well-known/mcp.json`	Read the authoritative MCP availability status and machine-surface links.

HTTP discovery

Content negotiation and Signposting

An agent can request a machine representation from the human paper URL instead of constructing a file path.

Request the object JSON

curl -L \
  -H "Accept: application/json" \
  https://datasetpapers.com/papers/{slug}/

Request the RO-Crate

curl -L \
  -H "Accept: application/ld+json" \
  https://datasetpapers.com/papers/{slug}/

Paper responses also advertise FAIR Signposting Link headers for canonical identifiers, metadata, licence, authors, and downloadable components.

Trust model

How an agent should interpret a result

`verification_status`

A status reported with a claim or version. Do not assume this alone means the result was independently reproduced.

`verification.json`

The independent re-execution record. A matched result means the published analysis code reproduced its declared values from pinned inputs.

`trust_distance`

The number of provenance hops from raw data. More hops mean more transformations to inspect, not automatically lower quality.

Experimental status

Formats, identifiers, and fields may change. Treat the corpus as evidence to inspect, not as an authoritative source or decision system.

MCP status

Why there is no hosted connection snippet yet

A hosted MCP client requires a working server endpoint. datasetpapers does not have one, and its local contract skeleton does not have an implemented data store, so publishing a remote connection snippet would imply access that does not exist.

Planned, not live

The authoritative discovery document reports "status": "planned" and "endpoint": null.

Proposed MCP surface

The design specifies read tools such as search_datasetpapers, get_datasetpaper, get_claim, list_claims, and get_provenance. Proposed write tools include propose_analysis, fork_datasetpaper, and submit_verification. These names describe planned interfaces; they cannot currently be used against a live corpus server.

Local skeleton, for contributors

Repository collaborators can build the stdio server and connect an MCP client to inspect its advertised tool contract. Corpus calls still fail with not implemented, and every write is rejected because authentication is unfinished. The repository README contains the exact local build and client configuration.

Read MCP discovery JSON Read the proposed specification MCP source (repository access required)

When a hosted endpoint becomes available, this page and /.well-known/mcp.json will publish the real URL, supported transport, authentication requirements, and client configuration. Until then, use the static HTTPS workflow above.