Basecite

io.github.paxton888Published by GitHub account paxton888v0.1.0Updated Oct 24, 2026

Tenant-scoped evidence intake and controlled AI context over MCP.

VerifiedStreamable HTTPWeb executableKnowledge & MemoryDeveloper Tools

Overview

AI-generated overview

BaseCite is a remote MCP server that returns public discovery and capability metadata and one bounded, tenant-scoped AI-context record by organization and file.

What you can do
Retrieve public developer, API, MCP, registry and safety-boundary links for BaseCite services and documentation, plus a machine-readable description of the service's capabilities and integration boundaries. Look up a single customer or solution-company submitted AI-context record by organization and upload identifier, returned with provenance and not-evaluated markers. The server is read-only and does not return raw files, bulk exports, or verification and ranking claims.
When to use it
Use it when an assistant needs to point people to BaseCite's public developer resources, check what the service does and where its access boundaries lie, or fetch one authorized AI-context record for a specific organization and upload.
Requirements
A remote Streamable HTTP endpoint; no local package or runtime is needed. The public discovery and capability tools need no credential. Accessing customer data requires tenant-scoped authentication, which the manifest does not declare.
Before you install
The AI-context lookup returns customer or solution-company submitted material, so treat it as tenant data and confirm authorization before use. The server states it does not verify truth or companies and makes no ranking claims, so its records should not be treated as verified facts. No credentials are declared in the manifest, but customer data access requires tenant-scoped authentication.

Installation

In SourceWeft

  1. Open Basecite in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.paxton888%2Fbasecite/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "basecite": {
      "type": "http",
      "url": "https://mcp.basecite.com/mcp"
    }
  }
}

README

BaseCite agent discovery

[skills.sh]

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

sh
npx skills add https://github.com/paxton888/basecite-agent-discovery --skill '*'

The repository publishes three distinct installable skills under skills/:

The skills contain no credentials, customer documents, or private BaseCite data.

Public developer resources

Official brand identity

BaseCite is the canonical product and service name for evidence-context infrastructure at https://basecite.com/.

Agent resources

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.

  • basecite_get_public_discovery: public developer, API, MCP, registry, and safety-boundary links
  • basecite_get_capabilities: machine-readable service capabilities and access boundaries
  • basecite_get_ai_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.

Source: README.md at commit a5da60a

Tools

3

basecite_get_public_discovery

Return BaseCite public developer, API, MCP, registry, and safety-boundary links. This tool never returns customer data and requires no credential.

Parametersinclude_registry

basecite_get_capabilities

Return the machine-readable capabilities and integration boundaries of the BaseCite service. This tool never returns customer data and requires no credential.

Parametersinclude_boundaries

basecite_get_ai_context

Return 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.

Parametersorg_idrequiredupload_idrequired

Version history

1
  1. v0.1.0LatestSep 20, 2026

Score

90% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

    Declare a license in the repository or the registry entry.