Skip to main content
Glama
90,911 servers. Updated

Matching MCP tools:

Matching MCP Connectors:

"Network Requests" matching MCP servers:

GET /v1/servers – MCP directory API reference
  • A
    license
    A
    quality
    B
    maintenance
    Multi-agent swarm orchestrator for AI workflows. Exposes blackboard read/write, agent dispatch, permission gating (AuthGuardian), token budget enforcement (FederatedBudget), and audit log tools over MCP. Supports 14 AI framework adapters including LangChain, AutoGen, CrewAI, Codex, and A2A — mix any frameworks in one swarm with race-condition-safe shared state.(Traffic light for agents)
    24
    557 npm
    76
    MIT
  • A
    license
    A
    quality
    A
    maintenance
    MCP server for parsing, validating, classifying, and normalizing Pinterest URLs locally, supporting pins, profiles, boards, and ideas URLs across Pinterest country domains without network requests.
    3
    30 npm
    MIT
  • A
    license
    A
    quality
    A
    maintenance
    Provides MCP tools for governed multi-vendor network device operations, including configuration management (backup, diff, merge, replace, rollback) and read-only queries (facts, interfaces, BGP, LLDP, ARP) via NAPALM, with optional NetBox source-of-truth integration.
    33
    MIT
  • A
    license
    Not graded
    quality
    F
    maintenance
    Acts as a proxy between your app and Reactotron, enabling AI assistants to read logs, inspect state, monitor network requests, and trigger custom commands.
    8 npm
    3
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    Read-only public Telegram group statistics from Limzo: search tracked communities and pull leaderboards, activity trends, member levels, and network-wide totals. No API key or account needed.
    3
    69 npm
    MIT
  • A
    license
    A
    quality
    A
    maintenance
    Enables AI agents to make pay-as-you-go AI inference requests through x402 with automatic Solana USDC payments, no API keys or registration, while enforcing configurable spending limits.
    3
    118 npm
    1
    MIT No Attribution
  • A
    license
    A
    quality
    B
    maintenance
    Provides local, deterministic scoring and detailed auditing of text for AI-writing patterns via two read-only tools, with no network calls or language models.
    4
    2
    9 npm
    3
    MIT
  • A
    license
    A
    quality
    A
    maintenance
    Free self-hosted web search for AI agents with multi-engine parallel search, semantic re-ranking, and native China network support. Zero API keys.
    2
    26
    MIT
  • A
    license
    A
    quality
    A
    maintenance
    Read visual bug reports from Feedbug in your AI coding agent: screenshot, console logs, failed network requests, session replay and the DOM context of the element the tester clicked. Trace the bug to its source file, comment and resolve without leaving the editor.
    7
    13 npm
    MIT
  • A
    license
    A
    quality
    A
    maintenance
    Screens the counterparty of an x402 payment before an agent pays it. One tool, screen_payment, checks address sanity, dynamic-payTo swaps, transport safety and your spend policy, then returns allow / review / block with the reasons — advisory only, and by default it runs with no key, no account and no network call.
    1
    1
    MIT
  • A
    license
    A
    quality
    C
    maintenance
    Scans diffs, files, and snippets for leaked secrets like AWS keys, GitHub tokens, and private keys, returning redacted findings while running fully locally without network calls.
    1
    MIT
  • A
    license
    A
    quality
    A
    maintenance
    Provides 13 ZIP tools for AI agents: inspect and list entries without extracting, verify integrity, extract with zip-slip, zip-bomb, and symlink guards, create deterministic reproducible archives, and modify ZIPs without recompression, all with no network access.
    13
    58 npm
    MIT
  • A
    license
    A
    quality
    A
    maintenance
    Call graph MCP server for Rust, Python, TypeScript, TSX, and JavaScript. Every caller and callee carries a resolution field showing how the reference was matched to a definition, plus multi-hop impact analysis for refactoring. Local-only, single binary, no network egress. Benchmarked against grep, ripgrep, and ctags on a 120-item hand-verified golden set, including the cases where it loses.
    3
    MIT
  • A
    license
    A
    quality
    A
    maintenance
    Queryable UniFi API documentation for Network, Protect, Site Manager, InnerSpace, Mobility and Carrier Fabric - endpoint search, schema drill-down and code examples in five languages. Read-only: it serves scraped docs and never connects to a controller.
    12
    10
    119 PyPI
    37
    MIT
  • A
    license
    A
    quality
    A
    maintenance
    Laravel Telescope-style debugging for Hono apps whose dashboard endpoint is also an MCP server: read recent exceptions with the request that produced them, recent requests filtered by status or duration, one request in full, and the slowest queries. Five read-only tools, zero runtime dependencies.
    5
    5
    216 npm
    26
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    Verifies blockchain-anchored timestamp proofs entirely on the user's machine, with five tools: hash a file, verify a file against a proof, verify a known hash against inline proof data, explain what a proof asserts, and create a new proof through ProofLedger. Verification recomputes the SHA-256 and walks the Merkle path locally instead of asking the issuer; only create uses the network.
    5
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    Honeypot threat intelligence for AI agents. Query 90 days of probe data from our sensor network: IP reputation, scanner classification, CVE probing trends, TLS/SSH/JA4 fingerprints. Free tier 500 credits/day, OAuth + bearer auth, streamable HTTP at https://mcp.honeylabs.net/mcp.
    7
    2
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    MCP server that ranks and deduplicates your GitHub pull request review queue across direct requests, team requests, and your own waiting PRs into a single prioritized list via one get_review_queue tool.
    2
    1
    1
    Apache 2.0