# Agent Core (npm · agent-core-mcp)

Deterministic computation tools for AI agents. Zero dependencies, no network, read-only.

- Trust score: 77/100 (medium)
- Change this week: +5
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-21

## Components

- npm · `agent-core-mcp`: 77/100 (this document), [markdown](https://verifymcp.io/servers/kinbinghua-lgtm-agent-core-mcp/agent-core-mcp.md), [page](https://verifymcp.io/servers/kinbinghua-lgtm-agent-core-mcp/agent-core-mcp)

## Channel facts

- Registry: `npm`
- Package: `agent-core-mcp`
- Version: `0.1.1`
- 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 2026-09-21.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - No production dependencies, so there is no dependency health to assess.
- **Provenance & Transparency**: 45/100
  - 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 9 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 86/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (excellent).
  - Tool/resource definitions use about 1610 tokens (~100/item across 16 items; 15 tools + 1 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 33/100
  - Stability observed for 10 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 98/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 95% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 15 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 17 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.

## Install

### How do I install the Agent Core MCP server?

Agent Core runs locally as an npm package, launched with npx -y agent-core-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 kinbinghua-lgtm-agent-core-mcp -- npx -y agent-core-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "kinbinghua-lgtm-agent-core-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "agent-core-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "kinbinghua-lgtm-agent-core-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "agent-core-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add kinbinghua-lgtm-agent-core-mcp -- npx -y agent-core-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "kinbinghua-lgtm-agent-core-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "agent-core-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add kinbinghua-lgtm-agent-core-mcp --command npx --arg -y --arg agent-core-mcp
```

### Hermes

```yaml
mcp_servers:
  kinbinghua-lgtm-agent-core-mcp:
    command: "npx"
    args: ["-y", "agent-core-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "kinbinghua-lgtm-agent-core-mcp": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "agent-core-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add kinbinghua-lgtm-agent-core-mcp -t stdio -c npx -a -y agent-core-mcp
```

### Other

```json
{
  "mcpServers": {
    "kinbinghua-lgtm-agent-core-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "agent-core-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.

### 2026-09-20 (score 77, +1)

No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-19 (score 76, +4)

- [functional improvement] Stability: unverified → 0.27

### 2026-09-12 (score 72, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-09-11 (score 57)

First indexed and scored.

## MCP tools (15)

### `diff_text` (~99 tokens)

Compute an exact line-by-line diff between two texts using a longest-common-subsequence algorithm. Returns per-line operations (equal/del/ins) with line numbers plus added/removed/unchanged counts. Exact and reproducible; refuses oversized input rather than hanging.

Input parameters:

- `a` (string, required): The original text
- `b` (string, required): The revised text
- `maxLines` (integer): Cap on returned diff lines (default 2000)

### `hash` (~111 tokens)

Compute a cryptographic hash of a UTF-8 string. Returns hex and base64 digests plus the UTF-8 byte length. Supports sha256 (default), sha512, sha1, md5, and HMAC variants via hmacKey. Use for content fingerprints, deduplication and integrity checks.

Input parameters:

- `algo` (string): Hash algorithm (default sha256)
- `hmacKey` (string): If set, compute HMAC with this key
- `text` (string, required): Text to hash

### `json_validate` (~81 tokens)

Check whether a string is valid JSON. On failure returns the parser message plus the computed line and column of the error. On success returns the top-level shape. Distinguishes valid-but-empty-object from invalid.

Input parameters:

- `describeTopLevel` (boolean): Include top-level keys or array length (default true)
- `text` (string, required): The JSON text to validate

### `json_query` (~123 tokens)

Extract a value from a JSON document by path, e.g. "a.b[0].c" or "$.items[3].name". Reports `resolved` (did the path reach a location) separately from `found` (is the value non-null), so absent is distinguishable from present-but-null. Failure types are specific: missing-key, out-of-range, not-an-array, not-an-object.

Input parameters:

- `json` (string, required): The JSON document as text
- `path` (string, required): Path, e.g. "a.b[0].c"

### `json_pick` (~56 tokens)

Resolve several paths against one JSON document in a single call. Cheaper than issuing many json_query calls when you need multiple fields.

Input parameters:

- `json` (string, required): The JSON document as text
- `paths` (array, required): Paths to resolve

### `text_stats` (~94 tokens)

Exact text statistics: Unicode code points, UTF-8 bytes, lines, non-empty lines, words, sentences, paragraphs, unique words, average word length and most frequent words. Word segmentation is Unicode-aware so non-Latin scripts are counted correctly. Use whenever a count must be exact.

Input parameters:

- `text` (string, required): Text to measure
- `topN` (integer): How many top words to return (default 10)

### `date_calc` (~121 tokens)

Interval between two ISO-8601 dates in days, weeks, months, years, hours, minutes, seconds or businessDays (Mon-Fri). Months and years use true calendar arithmetic, not 30/365-day approximations. All math is UTC.

Input parameters:

- `from` (string, required): Start date, e.g. 2026-01-15 or 2026-01-15T08:30:00Z
- `to` (string, required): End date, same formats
- `unit` (string): Unit for the result (default days)

### `date_add` (~89 tokens)

Offset an ISO-8601 date by days, weeks, months, years, hours, minutes or seconds. Negative amounts subtract. Calendar-correct across month ends and leap years.

Input parameters:

- `amount` (number, required): Amount to add; negative to subtract
- `date` (string, required): Base date, e.g. 2026-01-31
- `unit` (string): Unit (default days)

### `regex_extract` (~152 tokens)

Apply a regular expression and return every match with its index, numbered capture groups and named groups. Iteration and match counts are hard-capped so a pathological pattern cannot hang the host. The response includes a ReDoS risk assessment of the pattern.

Input parameters:

- `budgetMs` (integer): Execution deadline in milliseconds (default 1000, max 10000). Execution runs in a worker thread that is terminated on expiry.
- `flags` (string): Flags from g i m s u y (g is always applied)
- `maxMatches` (integer): Cap on returned matches (default 500)
- `pattern` (string, required): Regular expression source, without slashes
- `text` (string, required): Text to search

### `regex_analyze` (~72 tokens)

Statically analyse a regular expression for catastrophic backtracking (ReDoS): nested quantifiers, overlapping alternation inside repeated groups, backreferences under quantifiers, excessive wildcards. Returns a risk level and the specific reasons. The pattern is not executed.

Input parameters:

- `pattern` (string, required): Regular expression source to analyse

### `fuzzy_match` (~117 tokens)

Score every candidate string against a query using the Sorensen-Dice coefficient over character bigrams and return the best matches in descending order. Deterministic. Useful for deduplication, record linkage, typo-tolerant lookup and confirming which of several candidates was meant.

Input parameters:

- `haystack` (array, required): Candidate strings
- `needle` (string, required): The string to match against the list
- `threshold` (number): Minimum score to include (default 0)
- `topN` (integer): How many results (default 5)

### `similarity` (~52 tokens)

Sorensen-Dice similarity of two strings, from 0 (no shared character bigrams) to 1 (identical). One deterministic comparison.

Input parameters:

- `a` (string, required)
- `b` (string, required)

### `parse_table` (~132 tokens)

Parse delimited text into a header plus rows, handling quoted fields, escaped quotes, embedded delimiters and embedded newlines (RFC 4180 style). If no delimiter is given, the most frequent candidate on the first line is chosen and reported back. Use instead of splitting on commas, which breaks on any real CSV.

Input parameters:

- `delimiter` (string): Single-character delimiter; auto-detected if omitted
- `hasHeader` (boolean): Treat the first row as a header (default true)
- `maxRows` (integer): Row cap (default 5000)
- `text` (string, required): Delimited text

### `convert` (~143 tokens)

Convert a value between units of length, mass, time or data size. Cross-family conversions are rejected rather than silently producing nonsense. Data sizes: kb/mb/gb are decimal (1000), kib/mib/gib are binary (1024). Supported units: m, km, cm, mm, mi, yd, ft, in, nmi, kg, g, mg, t, lb, oz, s, min, h, d, b, kb, mb, gb, kib, mib, gib.

Input parameters:

- `from` (string, required): Source unit
- `to` (string, required): Target unit
- `value` (number, required): Numeric value to convert

### `base_convert` (~109 tokens)

Convert an integer string between bases 2 and 36 with arbitrary precision. Uses big-integer parsing, so values beyond IEEE-754 double precision (2^53) stay exact, which is exactly where naive conversion goes wrong. A leading 0b/0x/0o prefix is ignored.

Input parameters:

- `fromBase` (integer, required): Source base
- `toBase` (integer, required): Target base
- `value` (string, required): Integer as text, e.g. "ff" or "255"

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/kinbinghua-lgtm-agent-core-mcp/agent-core-mcp#diagnostics

## Score history

- 2026-09-21: 77
- 2026-09-20: 77
- 2026-09-19: 76
- 2026-09-18: 72
- 2026-09-17: 72
- 2026-09-16: 72
- 2026-09-15: 72
- 2026-09-14: 72
- 2026-09-13: 72
- 2026-09-12: 72
- 2026-09-11: 57

## Common questions

### What is the Agent Core MCP server?

Agent Core is an MCP server listed in the public MCP registry as io.github.kinbinghua-lgtm/agent-core-mcp. Deterministic computation tools for AI agents. Zero dependencies, no network, read-only. This page covers its npm package (agent-core-mcp).

### Is the Agent Core MCP server safe to use?

Agent Core scores 77 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 September 2026. It declares no install or post-install scripts. 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 Agent Core MCP server expose?

Agent Core exposes 15 tools: diff_text, hash, json_validate, json_query, json_pick, and 10 more. Their descriptions and schemas cost roughly 1,551 tokens of context every time the server is loaded.

### Is the Agent Core MCP server still maintained?

Agent Core is still listed as active in the MCP registry. We last reached this channel on 21 September 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 Agent Core MCP server under?

Agent Core 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

- npm package: https://www.npmjs.com/package/agent-core-mcp
- Socket report: https://socket.dev/npm/package/agent-core-mcp
- Repository: https://github.com/kinbinghua-lgtm/agent-core-mcp
- Website: https://www.npmjs.com/package/agent-core-mcp
- Changelog RSS feed: https://verifymcp.io/servers/kinbinghua-lgtm-agent-core-mcp/agent-core-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/kinbinghua-lgtm-agent-core-mcp/agent-core-mcp.json
- HTML version of this page: https://verifymcp.io/servers/kinbinghua-lgtm-agent-core-mcp/agent-core-mcp