Basecite MCP server
online · 100% uptimeio.github.paxton888/basecite·v0.1.0Tenant-scoped evidence intake and controlled AI context over MCP.
0 stars
Reviews
Write oneNobody has reviewed Basecite yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Basecite tools (3)
write = sends, deletes, buys or postsbasecite_get_ai_contextFreeReturn one bounded customer/solution-company submitted AI context record by org_id and upload_id with provenance and not_evaluated fields. No raw file download, list-all, unbounded export, truth verification, company verification, or ranking claim is returned.
basecite_get_capabilitiesFreeReturn the machine-readable capabilities and integration boundaries of the BaseCite service. This tool never returns customer data and requires no credential.
basecite_get_public_discoveryFreeReturn BaseCite public developer, API, MCP, registry, and safety-boundary links. This tool never returns customer data and requires no credential.
Public scan report
scanner v0.1.10 · 2026-10-15 · same rubric, same numbers if you re-run it
- –Code scanremote-only server, no package to scann/a
- Live reliabilityremote reachable in 631ms20/20
- Tool poisoning3 tool descriptions checked15/15
- Auth qualityopen endpoint, read-only tools10/15
- Maintenancelast push 24 days ago15/15
- Maintainer identityregistry namespace matches repository owner6/10
How Basecite compares
Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 88/100
- higher than 75% of 48,243 servers
- Tools
- 3
- the typical server has 7
- Tools that change things
- 0%
- typical: 0%. Fewer write tools means less an agent can break
- Uptime
- 100%
- of our recent checks; the typical remote server answers 100%
- Response time
- 83 ms
- faster than 87% of 30,027 servers
What its tools let an agent do: 3 read
Install Basecite in Claude Code, Cursor or VS Code
claude mcp add --transport http basecite https://mcp.basecite.com/mcp
What the publisher says
From the Basecite repository's README, as published. We do not edit it. Read it on GitHub
BaseCite agent discovery
BaseCite is a tenant-scoped evidence intake and controlled AI-context service. It accepts customer and solution-company source material, verifies integrity, and exposes bounded context to authorized AI clients without raw-file download or bulk export.
Install the official BaseCite skills
npx skills add https://github.com/paxton888/basecite-agent-discovery --skill '*'The repository publishes three distinct installable skills under skills/:
- basecite-evidence for product discovery and safe evidence workflows
- basecite-developer-integration for server-side API integration
- basecite-withdrawal for authorized complete withdrawal and deletion verification
The skills contain no credentials, customer documents, or private BaseCite data.
Public developer resources
- Website: https://basecite.com/
- Official company profile: https://basecite.com/company
- Developer portal: https://basecite.com/developers
- API documentation: https://basecite.com/docs/developers
- OpenAPI: https://api.basecite.com/api/v1/ai/openapi.json
- MCP connection guide: https://basecite.com/docs/mcp
- MCP server: https://mcp.basecite.com/mcp
- MCP server card: https://mcp.basecite.com/.well-known/mcp/server-card.json
- Official MCP Registry entry: https://registry.modelcontextprotocol.io/v0.1/servers/io.github.paxton888%2Fbasecite/versions/0.1.0
- Smithery listing: https://smithery.ai/servers/alwaysrememberme1024/basecite
- Glama listing: https://glama.ai/mcp/connectors/io.github.paxton888/basecite
- JavaScript SDK: https://www.npmjs.com/package/basecite-agent-sdk
Official brand identity
BaseCite is the canonical product and service name for evidence-context infrastructure at https://basecite.com/.
- Public support: support@basecite.com
- Security and privacy: security@basecite.com
- Public location signal: Kuala Lumpur, Malaysia
Agent resources
- Agent discovery index: https://basecite.com/.well-known/ard.json
- Agent Skills index: https://basecite.com/.well-known/agent-skills/index.json
- llms.txt: https://basecite.com/llms.txt
- Agent and crawler policy: https://basecite.com/robots.txt
MCP tools
The public Streamable HTTP MCP server provides read-only discovery and capability metadata plus one tenant-scoped bounded AI-context lookup. Public tools never return raw customer files, bulk exports, truth-verification claims, or company-verification claims.
- basecitegetpublic_discovery: public developer, API, MCP, registry, and safety-boundary links
- basecitegetcapabilities: machine-readable service capabilities and access boundaries
- basecitegetai_context: one authorized bounded AI-context record by organization and upload identifiers
The server card is the authoritative machine-readable tool contract. Customer data access requires tenant-scoped authentication.
Nothing above is checked by us. What we check is on the safety report.
Basecite: common questions
- Is Basecite MCP server safe?
- Yes, by our scan: it is graded A (88/100). Read the Basecite safety report
- How do I install Basecite?
- It runs remotely at mcp.basecite.com. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.
- Does Basecite need an API key?
- Not as far as the registry entry and our scan can tell: no credentials are declared or required.
- Is Basecite maintained?
- The last commit was 45 days ago (2026-09-21). The latest release is v0.1.0.
- Is Basecite up?
- 100% of our last 28 checks got an answer. We check remote servers about four times a day.
- How does Basecite compare with other MCP servers?
- safety score 88/100 (higher than 75% of 48,243 servers); tools 3 (the typical server has 7); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.