"Flat" matching MCP servers:

Flatten Claude Code sessions: keep every prompt and event verbatim, resume at a lower token count. An MCP server.

Enables managing multiple Gmail accounts under one OAuth client, with per-account access levels, cross-account search, and read/write operations via stdio or Streamable HTTP.

Enables users to query official business registers in the UK, Norway, Finland, and France for companies registered within a chosen window, filtered by industry code, activity words, name, or place. Each run returns one flat row per company with its register number, legal form, registration date, industry codes, activity text, address, and share capital, with optional deduplication across runs and a spend cap.

Enables reading replies, bounces, unsubscribes, meetings, interest changes, and LinkedIn replies from the user's own Instantly, Smartlead, HeyReach, and lemlist accounts, returning one flat row per event over a chosen time window. It is read-only and runs the polling work on Apify.

Resolves TypeScript config inheritance chains to reveal effective compiler options, resolves path aliases to physical files, and validates project references for AI agents.

Build AI trading agents on Eterna Hybrid Exchange (no-KYC perp DEX with flat 0.014%/0.035% fees). Works out of the box with fee estimation, venue comparison, setup guides and guarded agent prompts; add an Eterna token to bridge the official trading tools.

Enables AI agents to inspect, audit and safely edit locale JSON files across flat, nested, and namespaced layouts without loading whole files into the model context, with compact token-efficient reads and write paths that cannot drop keys or overwrite silently. Ships ten tools plus slash-command prompts for project info, key search, reference lookup, translation upserts, and missing-translation audits.

Enables users to design flat-pack furniture such as bookcases, cabinets, cubes and desks through natural-language conversation, then generates CNC-ready DXFs, cut and hardware lists, printable assembly instructions and a quote request for a fabricator.

An MCP server that allows AI assistants to programmatically manage Unleash feature flags through natural language, enabling operations like creating, updating, and retrieving feature flags across projects.

A community MCP server for float.com.

Enables agents to read, search, and propose durable knowledge stored as flat files in a GitHub repository, with every write opened as a pull request and domain owners approving changes in a web UI without touching git.

An MCP server that connects Claude (or any MCP compatible client) to your existing log infrastructure. Query, summarize, and trace logs in plain English across GCP Cloud Logging, AWS CloudWatch, Azure Log Analytics, Grafana Loki, and Elasticsearch without writing filter expressions or leaving your editor.

Enables AI agents to search and retrieve compounds, drugs, diseases, pathways, genes, enzymes, glycans, modules, and KO entries; fetch full parsed flat-file entries by ID; and list database contents through keyless REST tools.

Enables offline deterministic generation of SVG game assets such as creature sprites, flat icons, and seamless terrain tiles, with no external API calls or keys.

Turn any GraphQL API into MCP tools. Zero config, zero code. Auto-introspection, flat InputObject schemas for better LLM accuracy, smart truncation, retry logic with exponential backoff.

MCP proxy that bundles flat tool lists into hierarchical subcommand groups, reducing context token usage and improving tool discovery.

Publishes four flat, schema-light tools that let AI agents (including strict providers) search, describe, and invoke any of 139 reverse-engineering capabilities behind a persistent REA server. Enables file fingerprinting, inspection, and evidence-linked investigation of shipped software through plain-English requests, read-only by default.

Enables filtered, read-only querying of a Notion audit trail and action queue as four native tools (filtered lists and single-row lookups), with enum parameters validated against the live database schema and errors that report allowed values. It never writes to Notion, returns flat JSON rows, and keeps the integration token server-side.

A zero-ML-dependency keyword index MCP server for markdown context files, enabling fast search and retrieval of relevant files using RAKE and BM25, with a flat JSON index.

Token-efficient MCP server for Jira and Confluence that returns lean, flat responses to minimize token usage. Enables issue/comment/transition management, JQL/CQL search, and Confluence page operations.