samyama-graph
BLOCKgrade D · trust 67/100Graph-vector database that queried 1 billion edges for $2.50. Rust, OpenCypher, vector search, 14 graph algorithms. 74M nodes / 1B edges on a single machine.
billion edgescyphercypher query languagegraph algorithmsgraph databasegraph raghnswknowledge graphOverview
From the repository's own README, as read at the audited commit.
<p align="center"> <h1 align="center">Samyama Graph</h1> <p align="center">A Rust-native graph-vector database for GraphRAG, knowledge graphs, and billion-edge analytics.</p> <p align="center"> <strong>The graph database that queried 1 billion edges for $2.50</strong> </p> <p align="center"> <a href="https://github.com/samyama-ai/samyama-graph/releases"><img src="https://img.shields.io/badge/version-1.1.0-blue" alt="Version"></a> <a href="https://github.com/samyama-ai/samyama-graph/actions"><img src="https://img.shields.io/badge/tests-2238_passing-brightgreen" alt="Tests"></a> <a href="LICENSE"><img src="https://img.shields.io/badge/license-Apache_2.0-blue" alt="License"></a> <a href="https://graph.samyama.cloud/book/"><img src="https://img.shields.io/badge/book-read_the_docs-orange" alt="Book"></a> <a href="https://chat.whatsapp.com/Jjjkb3uWRDi1YMdfffaD9d"><img src="https://img.shields.io/badge/community-WhatsApp-25D366?logo=whatsapp&logoColor=white" alt="WhatsApp Community"></a> </p> <p align="center"> 💬 <strong><a href="https://chat.whatsapp.com/Jjjkb3uWRDi1YMdfffaD9d">Join the Samyama OSS community on WhatsApp</a></strong> — questions, help, and updates. </p></p>---## What is Samyama Graph?Samyama Graph is a Rust-native graph-vector database that lets developers store, query, search, and analyze connected data in one system.It brings together graph traversal, OpenCypher-style querying, vector search, graph algorithms, and Redis-compatible access, making it useful for GraphRAG, knowledge graphs, AI agent memory, and large-scale relationship analytics.### Quickstart#### Option 1 — Run with Docker Compose**Step 1 — Prerequisites**- ✅ Docker Desktop installed and running — [Watch setup video →](https://samyama.dev/videos)- ✅ No account or credentials needed — the image is public on GitHub Container Registry (`latest` is the newest release; pin a version such as `:1.8.0` for a reproducible setup)**Step 2 — Pull the Docker image**```bashdo
Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add samyama-sdk -- npx -y [email protected]
{
"mcpServers": {
"samyama-sdk": {
"command": "npx",
"args": [
"-y",
"[email protected]"
]
}
}
}Exposed tools (12) 10 read · 2 write · 0 destructive
| Tool | Risk | Description |
|---|---|---|
bad_tool | write | This tries to write |
count_nodes | read | Count all nodes |
cypher_query | write | Execute a read-only Cypher query against the graph. |
drug_neighbours | read | Drugs that share a pathway (4-hop scan — intentionally slow) |
heavy-skew | read | one value on ~50% of nodes, long tail — social/biomedical shape |
list_labels | read | Aggregate nodes by label |
mild-skew | read | 10 values, most common 3x the rarest |
rare_probe | read | Look up a specific rare drug by exact name |
sample_drugs | read | List drug names |
schema_info | read | Return the full graph schema including node types, edge types, |
top_people | read | Top people by some metric |
uniform | read | 10 values, equal counts — the distribution the estimator assumes |
Details
- Source
- samyama-ai/samyama-graph
- npm
samyama-sdk@1.8.0- PyPI
samyama- License
- Apache-2.0
- Stars
- 171 · pushed 0d ago
Trust audit
Do not install this without reading the findings. The audit found something that could harm you or your machine.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | FAIL |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (5 observation(s))
- Network
- declared (13 observation(s))
- Shell
- declared (2 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (22)
fn eval(&self, va: &[f32], vb: &[f32]) -> f32 {fn eval(&self, va: &[f32], vb: &[f32]) -> f32 {base_url = base_url or os.environ.get("SG_BASE_URL", "http://127.0.0.1:8080")export SG_BASE_URL="${SG_BASE_URL:-http://127.0.0.1:8080}"BASE_URL="http://127.0.0.1:${PORT_HTTP}"def __init__(self, base_url: str = "http://127.0.0.1:8080", graph: str = "default"):
ap.add_argument("--base-url", default="http://127.0.0.1:8080")fn exec(s: &GraphStore, q: &str) -> (usize, Duration) {let (r, d) = exec(s, q);
fn eval(expr: &str) -> String {resolve("../../etc/passwd"),MitreDef { technique_id: "T1048", name: "Exfiltration Over Alternative Protocol", tactic: "Exfiltration" },AttackStep { step: 5, source_name: "int-app-01", target_name: "int-db-01", technique: "T1048", description: "Database credentials exfiltrated via DNS tunneling" },println!(" Incoming IOC: Suspicious PowerShell beacon pattern detected.");" {fid}: Δbeds={:+.1} Δnurses={:+.1} Δdoctors={:+.1}",samyama, PyYAML
@types/node, typescript
case_studies/legal-judgments/cloud-demo.gif
ldbc-benchmark-results.png
sdk/python/examples/mcp-demo/samyama-mcp-demo.gif
sdk/python/examples/mcp-demo/samyama-mcp-demo.mp4
tests/algo-parity-reference.json
Gates applied: no_behavioural_pass.
Audited 2026-09-17 · audit v0.4.0 · source sha bba296964a8f · full audit: observations/trust-audit/mcp-server/samyama-ai__samyama-graph.json · Report an issue or request a re-scan
Audit history
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-09-17 | bba296964a8f | BLOCK | D | 67 | first audit |
Alternatives
Other servers in the same categories, safer ones first.
Questions
What is the samyama-graph MCP server?
Graph-vector database that queried 1 billion edges for $2.50. Rust, OpenCypher, vector search, 14 graph algorithms. 74M nodes / 1B edges on a single machine.
What tools does samyama-graph expose?
12 in total: 10 read-only, 2 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is samyama-graph safe to connect to an agent?
No — not without reading the findings first. The audit graded it D (67/100) and found 2 critical or high issues in the source. Each one is listed on this page with the file and line it is on.
What credentials does samyama-graph need?
No credential environment variables were found in its source, so it appears to need none.
How current is this page?
The grade is for one exact copy of the source (bba296964a8f), read on 2026-09-17. The repository is watched and re-audited when it changes.
Provenance: OBSERVED · read 2026-09-17 · job trust-audit-2026-09-17