About Snipara Project Intelligence
Snipara Project Intelligence is a hosted MCP server for project context and continuity across AI agents. This repository provides integration examples, discovery metadata, and reproducible benchmark evidence rather than the service implementation itself.
Key features
- 01Hosted project-specific MCP endpoint
- 02Runtime API-key or bearer-token authentication
- 03HTTP setup example
- 04MCP Registry metadata
- 05Reproducible benchmark evidence
- 06Python-standard-library evidence verifier
Use cases
- 01Connect an agent to hosted project context
- 02Set up the hosted MCP endpoint over HTTP
- 03Inspect public integration examples
- 04Verify benchmark calculations locally
MCP support
The project describes a hosted MCP server for project intelligence and context optimization. MCP clients connect to a project-specific HTTPS endpoint and authenticate at runtime with an API key or bearer token.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://api.snipara.com/mcp/{project_slug}claude mcp add --transport http snipara-snipara https://api.snipara.com/mcp/{project_slug}{"mcpServers":{"snipara-snipara":{"type":"http","url":"https://api.snipara.com/mcp/{project_slug}"}}}Open in Cursor{"servers":{"snipara-snipara":{"type":"http","url":"https://api.snipara.com/mcp/{project_slug}"}}}Open in VS Code{"mcpServers":{"snipara-snipara":{"type":"http","url":"https://api.snipara.com/mcp/{project_slug}"}}}{"mcpServers":{"snipara-snipara":{"serverUrl":"https://api.snipara.com/mcp/{project_slug}"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
https://api.snipara.com/mcp/{project_slug}Auth requiredTools
Details
From the project READMEsnipara-examples
Reproducible examples and evidence for Snipara Project Intelligence.
This repository keeps public integration examples, MCP discovery metadata, and benchmark evidence in one place. It is intentionally small: no customer data, private runbooks, internal ranking code, or credentials are included.
Start here
-
proof/checkpoint-handoff-2026-10contains a runnable Claude-produced checkpoint scenario, one paired native Codex continuation with/without Snipara and both independently validated candidates. -
server.jsondescribes the Hosted MCP server for the official MCP Registry. -
io.github.Snipara/sniparais the published official MCP Registry entry (1.0.0). -
examples/hosted-mcpshows the primary HTTP setup path without hard-coding a project or API key. -
benchmarks/hosted-context-2026-06contains the frozen June 19, 2026 context-selection evidence pack and its committedresults.json. -
proof/project-continuity-2026-07mirrors the measured summary from the public Project Intelligence proof replay, with its owned-repository and negative-control limits kept explicit.
Verify the benchmark evidence with only Python's standard library:
python3 benchmarks/hosted-context-2026-06/verify_results.py
The verifier checks the case manifest hash, case coverage, reported means, deltas, and token-reduction arithmetic. It does not claim that a live LLM run will be byte-for-byte deterministic.
Hosted MCP
Snipara is a Hosted MCP server for project intelligence and context optimization across AI agents. Each user connects a project-specific endpoint:
https://api.snipara.com/mcp/YOUR_PROJECT_SLUG
Authentication is supplied at runtime through X-API-Key or a bearer token.
Never commit an API key to this repository.
What this benchmark does and does not prove
The frozen evidence pack compares focused Snipara context against the first 32,000 tokens of the same indexed documentation corpus on 12 project-context questions. It preserves case-level scores so the published aggregates can be independently recomputed.
It is one hosted run per task, not a universal model-quality guarantee. Model behavior and the live hosted index can change, so future reruns should publish a new dated evidence pack instead of rewriting the historical result.
Additional controlled proof
The Project Intelligence proof replay measures a different question: whether continuity context changes what a coding agent finds before implementation and whether continuity-heavy scenarios pass across local, Codex CLI, and Claude runtimes. It is kept separate from the hosted-context benchmark because it uses a Snipara-owned repository and does not yet include a negative control where cold agents should already succeed.
Related projects
snipara-evalsprovides the deterministic Project Intelligence scoring library and CLI.snipara-companionprovides local workflow continuity and code-impact gates.snipara-memoryprovides the standalone open-source memory engine.- Snipara documentation documents the Hosted MCP, Project Intelligence, integrations, and security boundaries.
License
Apache-2.0. See LICENSE.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.