// mcp

MCP server

l0g exposes its data to AI agents through the Model Context Protocol, read-only. An agent can query Agent Surface, the OpenAPI contract, NDJSON feeds, Risk Diff, Black Box Recorder, claims, the evidence graph, sources, freshness, integrity, changefeed, signal history or full article text without scraping the site. No key, no authentication, no tracking.

Version française →

// why

AI agents increasingly read the web on behalf of humans, and they often do it badly: flattening HTML, losing context and mangling citations. For a site whose value depends on sourcing discipline, that is a risk. l0g publishes clean, attributable machine surfaces so the data can be reused exactly.

The Model Context Protocol extends the site philosophy: static-first, self-hosted, no tracking, no opaque proxy, read-only access and CC BY 4.0 reuse with attribution.

// endpoint

Streamable HTTP transport, request/response JSON mode.

https://l0g.fr/api/mcp

Read-only. The code and deployment procedure are public in the GitHub repository.

// resources

Documents and datasets are exposed as MCP resources. Agents can list resources with resources/list, read them with resources/read, and discover parameterized URIs with resources/templates/list.

URI	Content
`l0g://agent-manifest`	Agent Surface manifest
`l0g://openapi`	Complete OpenAPI contract
`l0g://freshness`	Corpus and signal freshness
`l0g://integrity`	Canonical SHA-256 fingerprints
`l0g://changes/latest`	Latest editorial changes and publications
`l0g://risk-diff`	Risk diff over 1, 7 and 30 days
`l0g://black-box`	Hashed point-in-time risk frames
`l0g://signals/current`	Current signal state
`l0g://signals/history`	Point-in-time signal history
`l0g://mcp/server`	MCP version, active SHA and server capabilities

// resource templates

Template	Content
`l0g://articles/{slug}`	First article page with metadata, references and text
`l0g://articles/{slug}{?section,offset,limit}`	Targeted article page by section, offset and limit
`l0g://articles/{slug}{?cursor}`	Article continuation through nextCursor
`l0g://guides/{slug}`	First guide page with metadata and text
`l0g://guides/{slug}{?section,offset,limit}`	Targeted guide page by section, offset and limit
`l0g://guides/{slug}{?cursor}`	Guide continuation through nextCursor
`l0g://claims/{claim_id}`	Claim-source relationship
`l0g://sources/{source_id}`	Primary source or cited host
`l0g://signals/{instrument}/current`	Current signal and history
`l0g://methodologies/{instrument}`	Methodology note

Templates enumerate known instances and propose variable completions. The public service is stateless and does not advertise live subscriptions; monitoring goes through l0g://changes/latest or get_changefeed.

// tools

Tools are reserved for operations: search, filtering, diff, replay, history, subgraph extraction or targeted reading. Full-text search remains local and deterministic, with no vector database or external provider. Long articles are paginated with continuation cursors, direct source access and separate references.

Tool	Arguments	Returns
`get_agent_manifest`	none	Agent Surface manifest: capabilities, endpoints, usage rules, proof policies and counters.
`get_risk_indices`	none	Normalized risk signals by instrument and 13FLOW confluence synthesis.
`get_signal_history`	key, limit	Level-change history, current signal state and 13FLOW confluence.
`get_risk_diff`	window	Risk diff over 1, 7 or 30 days: signals, sources, claims, models, articles and confidence.
`get_black_box`	date, limitFrames	Point-in-time replay of hashed risk frames, with explicit refusal for non-replayable dates.
`get_openapi_schema`	mode, path	Summarized, endpoint-targeted or complete OpenAPI contract.
`get_ndjson_feed`	feed, recordType, limit	Allowlisted NDJSON feeds: catalog, claims, evidence graph, changefeed and signal history.
`get_freshness`	limit	Corpus and signal freshness: observedAt, computedAt, expiration, coverage and policy.
`search_content`	query, mode, limit	Local deterministic full-text search on generated HTML, with catalog mode for audit.
`get_claims`	articleSlug, kind, query, limit	Filterable claim-source relationships with clickable references and dates when detectable.
`get_claim`	claimId	Single claim, resource links and parent article.
`get_claim_evidence`	claimId, limit	Prudent evidence level for one claim. Direct proof only when reviewed by humans.
`list_article_claims`	articleSlug, kind, limit	Claims for an article, usable as entry points into the evidence graph.
`find_claims_by_source`	sourceId, kind, limit	Claims linked to a primary source, a name or a cited host.
`get_source`	sourceId, limit	Primary source or cited host, with associated claims.
`get_evidence_graph`	articleSlug, nodeType, limit	Direct subgraph: articles → claims → references → sources.
`list_sources`	mode, limit	Institutional primary sources and hosts actually cited by claims.
`get_integrity`	path	Canonical SHA-256 fingerprints for Agent Surface, JSON and NDJSON surfaces.
`verify_artifact`	path, sha256	Allowlisted artifact verification through the integrity manifest.
`get_changefeed`	contentType, limit	Latest changes with objectId, current version/hash, diff status and semantic change.
`get_changes`	contentType, slug, since, limit	Changefeed filtered by type, slug and minimum date.
`list_recent_analyses`	limit	Latest analyses, newest first.
`list_guides`	none	Reference guides.
`search_by_topic`	topic, limit	Analyses attached to a topic hub.
`get_article`	slug, offset, cursor, limit, length, section	Paginated text for an analysis or guide, with nextCursor and separate references.

// connect

Inspect tools with the official inspector:

npx @modelcontextprotocol/inspector

Connect a desktop client through the local bridge:

npx mcp-remote https://l0g.fr/api/mcp

Example compatible-client configuration:

{
  "mcpServers": {
    "l0g": {
      "command": "npx",
      "args": ["mcp-remote", "https://l0g.fr/api/mcp"]
    }
  }
}

Minimal raw JSON-RPC cycle:

curl -s -X POST https://l0g.fr/api/mcp \
  -H 'Content-Type: application/json' \
  -H 'Accept: application/json, text/event-stream' \
  -d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-11-25","capabilities":{},"clientInfo":{"name":"curl","version":"0.1"}}}'

curl -s -X POST https://l0g.fr/api/mcp \
  -H 'Content-Type: application/json' \
  -H 'Accept: application/json, text/event-stream' \
  -d '{"jsonrpc":"2.0","method":"notifications/initialized"}'

curl -s -X POST https://l0g.fr/api/mcp \
  -H 'Content-Type: application/json' \
  -H 'Accept: application/json, text/event-stream' \
  -d '{"jsonrpc":"2.0","id":2,"method":"tools/list","params":{}}'

// security and design

Read-only. No tool writes anything, and article access goes through a slug allowlist, with no arbitrary URL fetch.
Not exposed directly. The service listens locally, behind Apache TLS and proxying.
Anti-hijacking. Host and Origin validation on each request, against DNS rebinding attacks.
Bounded. Per-IP rate limiting, bounded request size and hardened system service.
No sensitive data. Everything is public: no key, no authentication and no tracking.

// other machine access

Agent Surface: manifest, OpenAPI, claims, evidence graph, integrity, changefeed and NDJSON.
Public API: risk indices, canonical Debt Risk snapshot and level-change feed.
llms.txt and llms-full.txt: concise map and full corpus.