# io.github.sinhaKAN-ra/anumana (pypi · anumana-mcp)

Predict query cost, explain the plan, and rewrite it before you run it — 12 DB engines.

- Trust score: 68/100 (medium)
- Change this week: +43
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-16

## Components

- pypi · `anumana-mcp`: 68/100 (this document), [markdown](https://verifymcp.io/servers/sinhakan-ra-anumana/anumana-mcp.md), [page](https://verifymcp.io/servers/sinhakan-ra-anumana/anumana-mcp)

## Channel facts

- Registry: `pypi`
- Package: `anumana-mcp`
- Version: `0.2.1`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-16.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs hatchling.build at install time, a recognised build step with no custom scripting around it.
  - 0 of 30 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 48/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 10 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 73/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1203 tokens (~133/item across 9 items; 9 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 71/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 9 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 9 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### How do I install the io.github.sinhaKAN-ra/anumana MCP server?

io.github.sinhaKAN-ra/anumana runs locally as a PyPI package, launched with uvx anumana-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add sinhakan-ra-anumana -- uvx anumana-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "sinhakan-ra-anumana": {
      "command": "uvx",
      "args": [
        "anumana-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "sinhakan-ra-anumana": {
      "command": "uvx",
      "args": [
        "anumana-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add sinhakan-ra-anumana -- uvx anumana-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "sinhakan-ra-anumana": {
      "type": "local",
      "command": [
        "uvx",
        "anumana-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add sinhakan-ra-anumana --command uvx --arg anumana-mcp
```

### Hermes

```yaml
mcp_servers:
  sinhakan-ra-anumana:
    command: "uvx"
    args: ["anumana-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "sinhakan-ra-anumana": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "anumana-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add sinhakan-ra-anumana -t stdio -c uvx -a anumana-mcp
```

### Other

```json
{
  "mcpServers": {
    "sinhakan-ra-anumana": {
      "command": "uvx",
      "args": [
        "anumana-mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-15 (score 68, +28)

- [security improvement] Injection markers: unverified → pass
- [security] First check of Judged manipulation: pass
- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] MCP protocol: unverified → pass
- [functional] First check of Tool coverage: 0
- [functional] First check of Schema quality: fail
- [functional] First check of Schema quality: excellent
- [functional] First check of Destructive annotations: pass
- [functional] First check of Schema quality: fail
- [functional] First check of Tool coverage: 100

### 2026-10-13 (score 40, +1)

- [security regression] Provenance: unverified → fail
- [functional improvement] Security disclosure: unverified → pass

### 2026-10-12 (score 39, +14)

- [security regression] Provenance: fail → unverified
- [security improvement] Malware scan: unverified → pass
- [functional regression] Security disclosure: pass → unverified

### 2026-10-06 (score 25)

First indexed and scored.

## MCP tools (9)

### `list_targets` (~92 tokens)

List the databases Anumana is configured to analyse — each with its
name, engine, and whether it's diagnosable. Call this FIRST in a multi-DB
setup to see which target holds the data the user asked for, then pass
target=<name> to the other tools. In a single-DB setup you can omit target
and the one database is used. Never returns connection strings or secrets.

Output parameters:

- `result` (string)

### `list_policies` (~103 tokens)

List the operator's standing enforcement policies — the rules that can
BLOCK or WARN on a query regardless of what you intend. Each has a name,
scope (which target/engine), condition (risk tier and/or flag), and action
(block/warn/allow). preflight_query and suggest_query already apply these
and attach the verdict; call this to explain to a user WHY a query was
blocked. No policies configured means open by default (nothing blocked).

Output parameters:

- `result` (string)

### `preflight_query` (~146 tokens)

Before running ANY SQL query you (the agent) just wrote, check how
costly it will be on the real schema — WITHOUT executing it. Returns a
risk tier (cheap/moderate/expensive/dangerous), rows scanned vs returned,
scan strategy, and overhead flags (missing index, SELECT *, no LIMIT, N+1
/ nested-loop blowup). EXPLAIN only — never runs the query. In a multi-DB
setup pass target=<name> (see list_targets). For similarity search use
preflight_vector_search; with no DB use preflight_schema_only.

Input parameters:

- `sql` (string, required)
- `target` (string)

Output parameters:

- `result` (string)

### `preflight_vector_search` (~177 tokens)

Before running a VECTOR SIMILARITY SEARCH (pgvector: `ORDER BY embedding
\<-> $1 LIMIT k`, cosine `<=>`, inner-product `<#>`), check its cost WITHOUT
running it — for any RAG / semantic-search / nearest-neighbour query you
generate. Catches the vector traps a plain SQL check misses: brute-force
scan with no HNSW/IVFFlat index (FULL_VECTOR_SCAN), top_k too large
(TOP_K_TOO_LARGE), unbounded search (UNBOUNDED_VECTOR_SEARCH), and metadata-
filter/ANN recall loss (VECTOR_FILTER_INTERACTION). EXPLAIN only. Pass
target=<name> in a multi-DB setup; the target should be a pgvector engine.

Input parameters:

- `sql` (string, required)
- `target` (string)

Output parameters:

- `result` (string)

### `rewrite_query` (~127 tokens)

Rewrite a slow query into a cheaper, equivalent one and PROVE the
improvement by EXPLAIN-ing both and comparing planner cost. Call after a
preflight flags a query expensive/dangerous. Returns the rewritten query,
what changed, before/after cost, and index suggestions — ONLY suggesting a
btree index when the filter is selective enough to help (an HNSW index for
a vector target). Includes equivalence caveats. Pass target=<name> in a
multi-DB setup.

Input parameters:

- `sql` (string, required)
- `target` (string)

Output parameters:

- `result` (string)

### `explain_query_working` (~123 tokens)

Explain in plain English HOW a query behaves — two layers: (1) the
logical gather order (FROM -> WHERE -> GROUP BY -> HAVING -> SELECT ->
ORDER BY -> LIMIT), why 'LIMIT 10' can still be slow; and (2) the actual
physical plan the engine chose for THIS query, bottom-up. Call when a user
asks why a query is slow or how it runs. Teaching tool. Pass target=<name>
in a multi-DB setup.

Input parameters:

- `sql` (string, required)
- `target` (string)

Output parameters:

- `result` (string)

### `describe_schema_tool` (~149 tokens)

Read a database's REAL schema — tables/collections, columns/fields,
INDEXES, and row counts — so you can write a grounded, cost-aware query
BEFORE guessing. Call this FIRST when a user asks for data and you don't
already know the schema; it tells you which columns are indexed so your
query hits an index, not a full scan. READ-ONLY catalog access — never
reads data rows. If the schema can't be read it returns `need_from_user`
naming what to ask the user for. Pass target=<name> in a multi-DB setup;
combine with list_targets to find which DB has the data.

Input parameters:

- `target` (string)

Output parameters:

- `result` (string)

### `suggest_query` (~181 tokens)

Grade a query you (the agent) wrote for a user's data request and get
told whether to RUN it or REFINE it — the check step of generate->check->
refine. Workflow: (1) describe_schema_tool to learn columns + indexes,
(2) write a candidate for the user's intent, (3) call this. Returns
\`next_action`: 'accept' (cheap/moderate — run it) or 'refine' (expensive/
dangerous — here are the high-severity flags + a VERIFIED cheaper rewrite;
fix and call again). You write the SQL; Anumana owns cost truth. Bound your
loop to ~3 rounds. Pass target=<name> in a multi-DB setup.

Input parameters:

- `candidate_sql` (string, required)
- `intent` (string, required)
- `target` (string)

Output parameters:

- `result` (string)

### `preflight_schema_only` (~105 tokens)

Analyse a query against pasted CREATE TABLE DDL with NO database
connection — the zero-trust, offline front door. Call when the user gave
you their schema (DDL) but not DB credentials. Catches SELECT *, missing
LIMIT, un-indexed filter columns, LIKE '%...', functions on filtered
columns. HEURISTIC only (no live counts) and says so. No target needed.

Input parameters:

- `ddl` (string, required)
- `sql` (string, required)

Output parameters:

- `result` (string)

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/sinhakan-ra-anumana/anumana-mcp#diagnostics

## Score history

- 2026-10-16: 68
- 2026-10-15: 68
- 2026-10-14: 40
- 2026-10-13: 40
- 2026-10-12: 39
- 2026-10-09: 25
- 2026-10-06: 25

## Common questions

### What is the io.github.sinhaKAN-ra/anumana MCP server?

io.github.sinhaKAN-ra/anumana is an MCP server listed in the public MCP registry as io.github.sinhaKAN-ra/anumana. Predict query cost, explain the plan, and rewrite it before you run it, 12 DB engines. This page covers its PyPI package (anumana-mcp).

### Is the io.github.sinhaKAN-ra/anumana MCP server safe to use?

io.github.sinhaKAN-ra/anumana scores 68 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 16 October 2026. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the io.github.sinhaKAN-ra/anumana MCP server expose?

io.github.sinhaKAN-ra/anumana exposes 9 tools: list_targets, list_policies, preflight_query, preflight_vector_search, rewrite_query, and 4 more. Their descriptions and schemas cost roughly 1,203 tokens of context every time the server is loaded.

### Is the io.github.sinhaKAN-ra/anumana MCP server still maintained?

io.github.sinhaKAN-ra/anumana is still listed as active in the MCP registry. We last reached this channel on 16 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the io.github.sinhaKAN-ra/anumana MCP server under?

io.github.sinhaKAN-ra/anumana declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- PyPI project: https://pypi.org/project/anumana-mcp/
- Socket report: https://socket.dev/pypi/package/anumana-mcp
- Repository: https://github.com/sinhaKAN-ra/anumana
- Changelog RSS feed: https://verifymcp.io/servers/sinhakan-ra-anumana/anumana-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/sinhakan-ra-anumana/anumana-mcp.json
- HTML version of this page: https://verifymcp.io/servers/sinhakan-ra-anumana/anumana-mcp