MetaGO Algorithms
NPM · @METAGO-AI/ALGORITHMS
927 deterministic algorithms as 57 MCP tools: coupling, value, distance, correlation, reduction.
Available components
Last scanned (9 hours ago)
Scores higher than 68% of npm servers
Category AI and Machine Learning
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. How we score → Why this is hard to score →
Supply Chain Security98
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- No install/post-install scripts declared.Pass
- 30 of 94 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency48
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 8 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability63
- AI-judged instruction clarity (fair).Partial
- Tool/resource definitions use about 4138 tokens (~72/item across 57 items; 57 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
- No destabilizing schema changes in the last 30 days.Pass
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety75
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- 0 of 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "execute" implies "execute" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
- An AI judge read all 57 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 5 Nov 26 +1
- Security disclosure: unverified → pass ▲ functional
- 4 Nov 26 −1
- Security disclosure: pass → unverified ▼ functional
- 28 Oct 26 +1
- Stability: 0.97 → pass security
- 26 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.
- 24 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.
- 21 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 73 to 77. That category is still filling its 30-day observation window: 22 days of observed history at the previous scan, 23 at this one. The score rises as the window fills, whether or not the server changes.
- 19 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 67 to 70. That category is still filling its 30-day observation window: 20 days of observed history at the previous scan, 21 at this one. The score rises as the window fills, whether or not the server changes.
- 17 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 60 to 63. That category is still filling its 30-day observation window: 18 days of observed history at the previous scan, 19 at this one. The score rises as the window fills, whether or not the server changes.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 5 Nov 2026 · Analysed npm/@metago-ai/algorithms@1.0.2
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | npm |
Background: How many MCP packages publish verified provenance →
Dependencies 94 packages
| Packages resolved | 94 |
|---|---|
| Stale | 30 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
audit_check ~88
审计检查（20 个算法）。根据 operation 参数选择族内具体算法。operation 可选算法名关键词（如 cosine/euclidean/pearson）。不指定 operation 时执行族内首个算法。
| Name | Type | Req | Description |
|---|---|---|---|
| input | object | yes | 算法输入参数 |
| operation | string | – | 操作类型（算法名关键词），如 cosine/euclidean/pearson |
No output schema declared.
No examples provided.
bias_detect ~88
偏见检测（65 个算法）。根据 operation 参数选择族内具体算法。operation 可选算法名关键词（如 cosine/euclidean/pearson）。不指定 operation 时执行族内首个算法。
| Name | Type | Req | Description |
|---|---|---|---|
| input | object | yes | 算法输入参数 |
| operation | string | – | 操作类型（算法名关键词），如 cosine/euclidean/pearson |
No output schema declared.
No examples provided.
build_coupling_matrix ~68
构建耦生矩阵。适用：可视化关系网络。返回 NxN 矩阵。（算法 ID: ALG_T1_C_019）
| Name | Type | Req | Description |
|---|---|---|---|
| entities | object | yes | 实体列表 |
| relations | object | yes | 关系列表 |
No output schema declared.
No examples provided.
build_value_vector ~52
构建价值向量。适用：多维度价值量化。返回价值向量。（算法 ID: ALG_T1_C_026）
| Name | Type | Req | Description |
|---|---|---|---|
| dimensions | object | yes | 维度数据 |
No output schema declared.
No examples provided.
chebyshev_distance ~67
计算切比雪夫距离（L∞ 范数）。适用：棋盘距离。返回 ≥0。（算法 ID: ALG_T1_C_006）
| Name | Type | Req | Description |
|---|---|---|---|
| a | array | yes | 向量 A |
| b | array | yes | 向量 B |
No output schema declared.
No examples provided.
conflict_resolve ~89
冲突解决（49 个算法）。根据 operation 参数选择族内具体算法。operation 可选算法名关键词（如 cosine/euclidean/pearson）。不指定 operation 时执行族内首个算法。
| Name | Type | Req | Description |
|---|---|---|---|
| input | object | yes | 算法输入参数 |
| operation | string | – | 操作类型（算法名关键词），如 cosine/euclidean/pearson |
No output schema declared.
No examples provided.
cooccurrence_frequency ~60
共现频率计算。适用：关联分析、推荐。返回频率值。（算法 ID: ALG_T1_C_013）
| Name | Type | Req | Description |
|---|---|---|---|
| items | object | yes | 项列表 |
| window | object | yes | 窗口大小 |
No output schema declared.
No examples provided.
cosine_similarity ~84
计算两个向量的余弦相似度。适用：文本相似度、推荐系统、聚类。返回 [-1,1]，越接近 1 越相似。（算法 ID: ALG_T1_C_001）
| Name | Type | Req | Description |
|---|---|---|---|
| a | array | yes | 向量 A |
| b | array | yes | 向量 B |
No output schema declared.
No examples provided.
coupling_calculate ~90
耦生度计算（65 个算法）。根据 operation 参数选择族内具体算法。operation 可选算法名关键词（如 cosine/euclidean/pearson）。不指定 operation 时执行族内首个算法。
| Name | Type | Req | Description |
|---|---|---|---|
| input | object | yes | 算法输入参数 |
| operation | string | – | 操作类型（算法名关键词），如 cosine/euclidean/pearson |
No output schema declared.
No examples provided.
coupling_clustering ~59
耦生聚类分析。适用：关系网络分组。返回聚类结果。（算法 ID: ALG_T1_C_025）
| Name | Type | Req | Description |
|---|---|---|---|
| entities | object | yes | 实体列表 |
| k | number | yes | 聚类数 |
No output schema declared.
No examples provided.
coupling_trend ~50
耦生趋势分析。适用：时间序列关系变化。返回趋势方向。（算法 ID: ALG_T1_C_024）
| Name | Type | Req | Description |
|---|---|---|---|
| timeSeries | object | yes | 时间序列数据 |
No output schema declared.
No examples provided.
covariance ~56
协方差计算。适用：变量共变关系。返回协方差矩阵。（算法 ID: ALG_T1_C_030）
| Name | Type | Req | Description |
|---|---|---|---|
| a | array | yes | 数据 A |
| b | array | yes | 数据 B |
No output schema declared.
No examples provided.
creation_create ~87
创造生成（50 个算法）。根据 operation 参数选择族内具体算法。operation 可选算法名关键词（如 cosine/euclidean/pearson）。不指定 operation 时执行族内首个算法。
| Name | Type | Req | Description |
|---|---|---|---|
| input | object | yes | 算法输入参数 |
| operation | string | – | 操作类型（算法名关键词），如 cosine/euclidean/pearson |
No output schema declared.
No examples provided.
decision_decide ~89
决策制定（48 个算法）。根据 operation 参数选择族内具体算法。operation 可选算法名关键词（如 cosine/euclidean/pearson）。不指定 operation 时执行族内首个算法。
| Name | Type | Req | Description |
|---|---|---|---|
| input | object | yes | 算法输入参数 |
| operation | string | – | 操作类型（算法名关键词），如 cosine/euclidean/pearson |
No output schema declared.
No examples provided.
detect_asymmetry ~55
检测不对称耦生。适用：发现单向依赖。返回不对称对列表。（算法 ID: ALG_T1_C_023）
| Name | Type | Req | Description |
|---|---|---|---|
| pairs | object | yes | 对列表 |
No output schema declared.
No examples provided.
dialog_manage ~87
对话管理（20 个算法）。根据 operation 参数选择族内具体算法。operation 可选算法名关键词（如 cosine/euclidean/pearson）。不指定 operation 时执行族内首个算法。
| Name | Type | Req | Description |
|---|---|---|---|
| input | object | yes | 算法输入参数 |
| operation | string | – | 操作类型（算法名关键词），如 cosine/euclidean/pearson |
No output schema declared.
No examples provided.
dice_coefficient ~76
计算 Dice 系数（2*交集/(|A|+|B|)）。适用：字符串/集合相似度。返回 [0,1]。（算法 ID: ALG_T1_C_003）
| Name | Type | Req | Description |
|---|---|---|---|
| a | array | yes | 集合 A |
| b | array | yes | 集合 B |
No output schema declared.
No examples provided.
euclidean_distance ~63
计算欧氏距离。适用：空间距离、KNN。返回 ≥0 的数值。（算法 ID: ALG_T1_C_004）
| Name | Type | Req | Description |
|---|---|---|---|
| a | array | yes | 向量 A |
| b | array | yes | 向量 B |
No output schema declared.
No examples provided.
evaluate_bidirectional ~68
双向耦生度评估。适用：分析双向关系强度。返回 {forward, backward, symmetric}。（算法 ID: ALG_T1_C_015）
| Name | Type | Req | Description |
|---|---|---|---|
| backward | object | yes | 反向数据 |
| forward | object | yes | 正向数据 |
No output schema declared.
No examples provided.
evolution_evolve ~89
进化计算（50 个算法）。根据 operation 参数选择族内具体算法。operation 可选算法名关键词（如 cosine/euclidean/pearson）。不指定 operation 时执行族内首个算法。
| Name | Type | Req | Description |
|---|---|---|---|
| input | object | yes | 算法输入参数 |
| operation | string | – | 操作类型（算法名关键词），如 cosine/euclidean/pearson |
No output schema declared.
No examples provided.
execute ~73
异步执行任意算法（支持所有 927 算法）。当用户指定算法 ID 时使用。返回 {success, output, provenance, durationMs}。
| Name | Type | Req | Description |
|---|---|---|---|
| id | string | yes | 算法 ID，如 ALG_T1_C_001 |
| input | object | yes | 算法输入参数 |
No output schema declared.
No examples provided.
execute_sync ~74
同步执行 T1 算法（300 个同步算法）。比 execute 更快，但不支持 async handler。返回 {success, output, provenance, durationMs}。
| Name | Type | Req | Description |
|---|---|---|---|
| id | string | yes | 算法 ID，如 ALG_T1_C_001 |
| input | object | yes | 算法输入参数 |
No output schema declared.
No examples provided.
extract_pca ~64
主成分提取（PCA）。适用：特征提取、降维。返回主成分。（算法 ID: ALG_T1_C_028）
| Name | Type | Req | Description |
|---|---|---|---|
| components | number | yes | 成分数 |
| data | object | yes | 数据矩阵 |
No output schema declared.
No examples provided.
frequency_process ~88
频率处理（48 个算法）。根据 operation 参数选择族内具体算法。operation 可选算法名关键词（如 cosine/euclidean/pearson）。不指定 operation 时执行族内首个算法。
| Name | Type | Req | Description |
|---|---|---|---|
| input | object | yes | 算法输入参数 |
| operation | string | – | 操作类型（算法名关键词），如 cosine/euclidean/pearson |
No output schema declared.
No examples provided.
fuzzy_string_match ~68
模糊字符串匹配。适用：拼写纠错、模糊搜索。返回 [0,1]。（算法 ID: ALG_T1_C_011）
| Name | Type | Req | Description |
|---|---|---|---|
| a | array | yes | 字符串 A |
| b | array | yes | 字符串 B |
No output schema declared.
No examples provided.
get_algorithm_info ~51
获取算法元数据（ID/名称/族/层级/复杂度/输入输出 schema/描述）。当需要了解算法详情时使用。
| Name | Type | Req | Description |
|---|---|---|---|
| id | string | yes | 算法 ID |
No output schema declared.
No examples provided.
get_statistics ~33
获取算法全局统计（总数/已实现数/各层级数/各族数）。无需参数。
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
idea_generate ~87
创意生成（20 个算法）。根据 operation 参数选择族内具体算法。operation 可选算法名关键词（如 cosine/euclidean/pearson）。不指定 operation 时执行族内首个算法。
| Name | Type | Req | Description |
|---|---|---|---|
| input | object | yes | 算法输入参数 |
| operation | string | – | 操作类型（算法名关键词），如 cosine/euclidean/pearson |
No output schema declared.
No examples provided.
identify_strong_pairs ~60
识别强耦生对。适用：发现关键关系。返回强对列表。（算法 ID: ALG_T1_C_018）
| Name | Type | Req | Description |
|---|---|---|---|
| pairs | object | yes | 对列表 |
| threshold | number | yes | 阈值 |
No output schema declared.
No examples provided.
identify_weak_pairs ~62
识别弱耦生对。适用：发现需要加强的关系。返回弱对列表。（算法 ID: ALG_T1_C_017）
| Name | Type | Req | Description |
|---|---|---|---|
| pairs | object | yes | 对列表 |
| threshold | number | yes | 阈值 |
No output schema declared.
No examples provided.
intuition_gauge ~90
直觉度量（49 个算法）。根据 operation 参数选择族内具体算法。operation 可选算法名关键词（如 cosine/euclidean/pearson）。不指定 operation 时执行族内首个算法。
| Name | Type | Req | Description |
|---|---|---|---|
| input | object | yes | 算法输入参数 |
| operation | string | – | 操作类型（算法名关键词），如 cosine/euclidean/pearson |
No output schema declared.
No examples provided.
is_superconductive ~61
超导态判定（耦生度>1）。适用：识别超强耦合关系。返回 boolean。（算法 ID: ALG_T1_C_016）
| Name | Type | Req | Description |
|---|---|---|---|
| couplingScore | number | yes | 耦生分数 |
No output schema declared.
No examples provided.
jaccard_coefficient ~79
计算两个集合的 Jaccard 相似系数（交集/并集）。适用：集合相似度。返回 [0,1]。（算法 ID: ALG_T1_C_002）
| Name | Type | Req | Description |
|---|---|---|---|
| a | array | yes | 集合 A（数组） |
| b | array | yes | 集合 B（数组） |
No output schema declared.
No examples provided.
kendall_tau ~63
计算 Kendall Tau 秩相关系数。适用：序数变量相关性。返回 [-1,1]。（算法 ID: ALG_T1_C_009）
| Name | Type | Req | Description |
|---|---|---|---|
| a | array | yes | 数据 A |
| b | array | yes | 数据 B |
No output schema declared.
No examples provided.
learning_learn ~88
学习训练（49 个算法）。根据 operation 参数选择族内具体算法。operation 可选算法名关键词（如 cosine/euclidean/pearson）。不指定 operation 时执行族内首个算法。
| Name | Type | Req | Description |
|---|---|---|---|
| input | object | yes | 算法输入参数 |
| operation | string | – | 操作类型（算法名关键词），如 cosine/euclidean/pearson |
No output schema declared.
No examples provided.
list_algorithms ~84
列出算法列表，可按 tier（T1/T2/T3）或 family（COUPLING/VALUE/BIAS 等）过滤。返回 {total, algorithms}。
| Name | Type | Req | Description |
|---|---|---|---|
| family | string | – | 按族过滤，如 COUPLING |
| limit | number | – | 返回数量限制 |
| tier | string | – | 按层级过滤 |
No output schema declared.
No examples provided.
list_families ~27
列出所有 20 个算法族及其算法数量。无需参数。
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
logic_reason ~89
逻辑推理（65 个算法）。根据 operation 参数选择族内具体算法。operation 可选算法名关键词（如 cosine/euclidean/pearson）。不指定 operation 时执行族内首个算法。
| Name | Type | Req | Description |
|---|---|---|---|
| input | object | yes | 算法输入参数 |
| operation | string | – | 操作类型（算法名关键词），如 cosine/euclidean/pearson |
No output schema declared.
No examples provided.
manhattan_distance ~65
计算曼哈顿距离（L1 范数）。适用：网格距离。返回 ≥0。（算法 ID: ALG_T1_C_005）
| Name | Type | Req | Description |
|---|---|---|---|
| a | array | yes | 向量 A |
| b | array | yes | 向量 B |
No output schema declared.
No examples provided.
memory_operate ~89
记忆操作（49 个算法）。根据 operation 参数选择族内具体算法。operation 可选算法名关键词（如 cosine/euclidean/pearson）。不指定 operation 时执行族内首个算法。
| Name | Type | Req | Description |
|---|---|---|---|
| input | object | yes | 算法输入参数 |
| operation | string | – | 操作类型（算法名关键词），如 cosine/euclidean/pearson |
No output schema declared.
No examples provided.
negentropy_measure ~91
负熵测量（49 个算法）。根据 operation 参数选择族内具体算法。operation 可选算法名关键词（如 cosine/euclidean/pearson）。不指定 operation 时执行族内首个算法。
| Name | Type | Req | Description |
|---|---|---|---|
| input | object | yes | 算法输入参数 |
| operation | string | – | 操作类型（算法名关键词），如 cosine/euclidean/pearson |
No output schema declared.
No examples provided.
normalize_coupling ~79
归一化耦生分数到 [0,1]。适用：标准化比较。返回归一化值。（算法 ID: ALG_T1_C_020）
| Name | Type | Req | Description |
|---|---|---|---|
| max | number | yes | 最大值 |
| min | number | yes | 最小值 |
| score | number | yes | 原始分数 |
No output schema declared.
No examples provided.
pearson_correlation ~63
计算皮尔逊相关系数。适用：线性相关性分析。返回 [-1,1]。（算法 ID: ALG_T1_C_007）
| Name | Type | Req | Description |
|---|---|---|---|
| a | array | yes | 数据 A |
| b | array | yes | 数据 B |
No output schema declared.
No examples provided.
proactive_suggest ~88
主动建议（20 个算法）。根据 operation 参数选择���内具体算法。operation 可选算法名关键词（如 cosine/euclidean/pearson）。不指定 operation 时执行族内首个算法。
| Name | Type | Req | Description |
|---|---|---|---|
| input | object | yes | 算法输入参数 |
| operation | string | – | 操作类型（算法名关键词），如 cosine/euclidean/pearson |
No output schema declared.
No examples provided.
reasoning_chain ~87
推理链（49 个算法）。根据 operation 参数选择族内具体算法。operation 可选算法名关键词（如 cosine/euclidean/pearson）。不指定 operation 时执行族内首个算法。
| Name | Type | Req | Description |
|---|---|---|---|
| input | object | yes | 算法输入参数 |
| operation | string | – | 操作类型（算法名关键词），如 cosine/euclidean/pearson |
No output schema declared.
No examples provided.
record_symmetric ~74
记录对称耦生关系。适用：双向等权关系存储。返回记录结果。（算法 ID: ALG_T1_C_022）
| Name | Type | Req | Description |
|---|---|---|---|
| entityA | object | yes | 实体 A |
| entityB | object | yes | 实体 B |
| score | number | yes | 分数 |
No output schema declared.
No examples provided.
reduce_dimension ~61
降维计算。适用：高维数据可视化。返回降维后数据。（算法 ID: ALG_T1_C_027）
| Name | Type | Req | Description |
|---|---|---|---|
| data | object | yes | 高维数据 |
| targetDim | number | yes | 目标维度 |
No output schema declared.
No examples provided.
search_algorithms ~56
按关键词搜索算法（在名称/描述/关键词中匹配）。返回匹配的算法列表。
| Name | Type | Req | Description |
|---|---|---|---|
| limit | number | – | 返回数量限制，默认 20 |
| query | string | yes | 搜索关键词 |
No output schema declared.
No examples provided.
security_assess ~89
安全评估（48 个算法）。根据 operation 参数选择族内具体算法。operation 可选算法名关键词（如 cosine/euclidean/pearson）。不指定 operation 时执行族内首个算法。
| Name | Type | Req | Description |
|---|---|---|---|
| input | object | yes | 算法输入参数 |
| operation | string | – | 操作类型（算法名关键词），如 cosine/euclidean/pearson |
No output schema declared.
No examples provided.
semantic_similarity ~63
语义相似度计算。适用：自然语言语义匹配。返回 [0,1]。（算法 ID: ALG_T1_C_012）
| Name | Type | Req | Description |
|---|---|---|---|
| a | array | yes | 文本 A |
| b | array | yes | 文本 B |
No output schema declared.
No examples provided.
How do I install the MetaGO Algorithms MCP server?
MetaGO Algorithms runs locally as an npm package, launched with npx -y @metago-ai/algorithms. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · @metago-ai/algorithms
claude mcp add metago-ai-metago-algorithms -- npx -y @metago-ai/algorithms
What is the MetaGO Algorithms MCP server?
MetaGO Algorithms is an MCP server listed in the public MCP registry as io.github.metago-ai/metago-algorithms. 927 deterministic algorithms as 57 MCP tools: coupling, value, distance, correlation, reduction. This page covers its npm package (@metago-ai/algorithms).
Is the MetaGO Algorithms MCP server safe to use?
MetaGO Algorithms scores 81 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 November 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 MetaGO Algorithms MCP server expose?
MetaGO Algorithms exposes 57 tools: audit_check, bias_detect, build_coupling_matrix, build_value_vector, chebyshev_distance, and 52 more. Their descriptions and schemas cost roughly 4,138 tokens of context every time the server is loaded.
Is the MetaGO Algorithms MCP server still maintained?
MetaGO Algorithms is still listed as active in the MCP registry. We last reached this channel on 5 November 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 MetaGO Algorithms MCP server under?
MetaGO Algorithms declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.