Skip to main content
Glama

similarity-search-api-sdk

Server Details

Stateless NMI + cosine fusion with entropy-driven alpha calibration

Status
Healthy
Last Tested
Transport
Streamable HTTP
URL
Repository
nexus-mcp-infra/similarity-search-api-sdk
GitHub Stars
0

Glama MCP Gateway

Connect through Glama MCP Gateway for full control over tool access and complete visibility into every call.

MCP client
Glama
MCP server

Full call logging

Every tool call is logged with complete inputs and outputs, so you can debug issues and audit what your agents are doing.

Tool access control

Enable or disable individual tools per connector, so you decide what your agents can and cannot do.

Managed credentials

Glama handles OAuth flows, token storage, and automatic rotation, so credentials never expire on your clients.

Usage analytics

See which tools your agents call, how often, and when, so you can understand usage patterns and catch anomalies.

100% free. Your data is private.
Tool DescriptionsA

Average 4.6/5 across 3 of 3 tools scored.

Server CoherenceA
Disambiguation5/5

Each tool has a clearly distinct purpose: one estimates corpus entropy, one ranks items against a query, and one scores a single pair. There is no overlap or ambiguity.

Naming Consistency5/5

All tool names follow the same pattern: prefix 'nexus_similarity_search_api_' followed by a descriptive verb_noun in snake_case (e.g., estimate_corpus_entropy_profile, rank_items_by_nmi_cosine_fusion). The naming is perfectly consistent.

Tool Count5/5

Three tools is a reasonable count for this domain, covering entropy estimation, corpus ranking, and pairwise scoring without unnecessary clutter.

Completeness4/5

The tool set covers the core workflows (pre-check, ranking, explainability). Missing a dedicated tool for API key or payment management, but these are handled as parameters, so the gap is minor.

Available Tools

3 tools
nexus_similarity_search_api_estimate_corpus_entropy_profileAInspect

Computes the aggregate entropy-calibrated alpha for a corpus without running a full search -- useful to inspect before committing to a large rank_items_by_nmi_cosine_fusion call. Returns a single aggregate corpus_entropy value, NOT a per-dimension breakdown -- the real logic only exposes the mean marginal entropy across dimensions, not H(X_d) per individual dimension. Do NOT use expecting per-dimension granularity. Requires a valid api_key (same as X-API-Key) and an x402 payment.

ParametersJSON Schema
NameRequiredDescriptionDefault
n_binsNoNumber of histogram bins for entropy discretization. Must be between 3 and 50; should match the n_bins used in rank_items_by_nmi_cosine_fusion for the profile to be consistent.
api_keyYesAPI key required for this paid operation -- same secret configured as X-API-Key on the REST endpoints (SIMILARITY_API_KEY). Payment (x402) alone is not sufficient; both gates must pass.
corpus_vectorsYesList of dense numeric vectors for which to compute the aggregate entropy and calibrated alpha. Each inner array must be the same length. Maximum 500000 entries.
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full burden. It discloses that the return is a single aggregate corpus_entropy value, not per-dimension breakdown, and that only mean marginal entropy is exposed. Also mentions authentication and payment requirements. Missing side-effect or performance details, but adequate for a read-only estimate.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Description is front-loaded with purpose, uses dashes for emphasis, and conveys essential information in a single sentence. It is not overly verbose, but the structure could be slightly clearer with separate sentences. Overall, every phrase contributes value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema, description adequately explains the returned value (single aggregate, not per-dimension) and its role as a pre-check. It covers authentication requirements. Lacks details on error handling or exact return format, but sufficient for the tool's simplicity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline 3. Description adds minimal extra meaning beyond schema, except advising that n_bins should match that used in the sibling tool. The api_key and corpus_vectors descriptions are already in schema, so no significant additional semantic value.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states it computes aggregate entropy-calibrated alpha for a corpus without running full search, and distinguishes from sibling 'rank_items_by_nmi_cosine_fusion' by positioning as a pre-check. Also clarifies it returns a single value, not per-dimension, making the tool's purpose specific and unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly suggests using it before committing to a large rank_items_by_nmi_cosine_fusion call, and warns against expecting per-dimension granularity. Mentions required api_key and x402 payment. Could be more explicit about when to prefer siblings, but the context is clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

nexus_similarity_search_api_rank_items_by_nmi_cosine_fusionAInspect

Ranks a corpus of items against a query vector using a calibrated fusion score (alpha * cosine + (1-alpha) * NMI_normalizado), where alpha is auto-derived from the corpus's marginal entropy unless overridden. Results are identified by their 0-indexed position in corpus_vectors (this tool does not accept explicit item IDs). Use this when you need semantically-calibrated similarity over a stateless corpus of up to 500k items without a vector database. Do NOT use for purely geometric nearest-neighbor search where NMI overhead is unnecessary, nor for corpora larger than 500k items per call. Requires a valid api_key (same as X-API-Key) and an x402 payment.

ParametersJSON Schema
NameRequiredDescriptionDefault
top_kNoNumber of top-ranked results to return, ordered by descending fusion score. Capped at 1000 by the core service regardless of corpus size.
n_binsNoNumber of histogram bins used to discretize continuous dimensions when estimating NMI. Must be between 3 and 50.
api_keyYesAPI key required for this paid operation -- same secret configured as X-API-Key on the REST endpoints (SIMILARITY_API_KEY). Payment (x402) alone is not sufficient; both gates must pass.
query_vectorYesDense numeric vector representing the query item. Must have the same dimensionality as all corpus_vectors entries.
alpha_overrideNoFixed alpha weight for cosine component in [0.0, 1.0]. If omitted, alpha is auto-calibrated from corpus entropy. Set to 1.0 to use pure cosine; 0.0 for pure NMI.
corpus_vectorsYesList of dense numeric vectors forming the corpus to rank against. Each inner array must match query_vector dimensionality. Maximum 500000 entries.
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided; description discloses auto-alpha derivation, result identification by index, stateless corpus, and constraints (500k items). No contradictions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Dense, well-structured description with no wasted words. Each sentence adds necessary information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 6 parameters, no output schema, and high complexity, the description covers purpose, algorithm, result format, usage constraints, and authentication. Completely adequate.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, but description adds meaning with the fusion formula, auto-calibration, and contextual constraints (e.g., alpha_override behavior, n_bins histogram role).

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool ranks a corpus against a query using a calibrated fusion score, and distinguishes it from sibling tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states when to use (semantically-calibrated similarity) and when not to (pure geometric search, corpora >500k items). Also mentions requirements like api_key and x402 payment.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

nexus_similarity_search_api_score_pair_nmi_cosineAInspect

Computes the NMI-cosine fusion score for exactly one (query, target) vector pair at a fixed alpha. Use for explainability, debugging, or unit-level validation of fusion scores before running full corpus ranking. Unlike corpus-level ranking, alpha is NOT auto-calibrated for a single pair -- the real logic requires a fixed alpha (default 0.5); pass alpha explicitly for a specific blend. Do NOT use in a loop to score many pairs; batch them into rank_items_by_nmi_cosine_fusion instead. Requires a valid api_key (same as X-API-Key) and an x402 payment.

ParametersJSON Schema
NameRequiredDescriptionDefault
alphaNoFixed alpha weight for the cosine component in [0.0, 1.0], applied as-is -- not auto-calibrated. Default 0.5 matches the core service default.
n_binsNoHistogram bins for NMI discretization. Must be between 3 and 50.
api_keyYesAPI key required for this paid operation -- same secret configured as X-API-Key on the REST endpoints (SIMILARITY_API_KEY). Payment (x402) alone is not sufficient; both gates must pass.
vector_aYesFirst dense numeric vector of the pair. Must have the same dimensionality as vector_b.
vector_bYesSecond dense numeric vector of the pair. Must have the same dimensionality as vector_a.
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description carries burden. Discloses that alpha is not auto-calibrated, that both api_key and x402 payment are required, and that it handles only single pairs. Does not describe return value or error behavior, but overall adequately transparent for a focused single-pair scoring tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two concise sentences plus a clear negative usage note. Front-loaded with core purpose and usage. No fluff.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema, but tool is for a narrow purpose. Description covers purpose, when/not to use, parameters, and requirements. Missing explicit return value description, but acceptable given the tool's focus and schema coverage.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3. Description adds context: explains alpha is fixed (not auto-calibrated), api_key is same as X-API-Key, and that vector_a and vector_b must have same dimensionality. Adds meaningful usage guidance beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states the tool computes NMI-cosine fusion score for one pair at fixed alpha. Distinguishes from sibling tools by mentioning 'Unlike corpus-level ranking' and referencing the batch tool 'rank_items_by_nmi_cosine_fusion'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states when to use: 'for explainability, debugging, or unit-level validation'. Explicitly advises against looping: 'Do NOT use in a loop to score many pairs; batch them into rank_items_by_nmi_cosine_fusion instead'. Also notes requirements: 'needs valid api_key and x402 payment'.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Discussions

No comments yet. Be the first to start the discussion!

Try in Browser

Your Connectors

Sign in to create a connector for this server.