"An agent for conducting research" matching MCP servers:

PII detection agent

Two-way Burp Suite MCP bridge enabling AI agents to capture traffic, analyze endpoints, queue scans, and send findings back to Burp.

Security scanning, prompt injection detection, secret leak detection, and agent permission auditing for AI agent workflows.

An MCP server for using Bitwarden Secrets Manager as durable credential storage for agent workflows, enabling secure secret storage, retrieval, and injection into trusted executables.

agent-bom is an open security scanner and self-hosted control plane for AI, MCP, and cloud infrastructure. The default scan profile in MCP server mode exposes 8 MCP tools. Additional profiles provide inventory, findings, compliance, graph, and runtime workflows. See the published Glama release for its packaged version.

Enables MCP clients to run local scans for known AI coding-assistant backdoor indicators and risky Claude Code/MCP configuration patterns, returning findings directly in chat.

Secures MCP tools as an OAuth 2.1 resource server, validating short-lived delegated tokens, enforcing policy-as-code, and auditing AI agent actions.

Agent Vault is a local credential vault for AI agents. It enables agents to use secrets by name without ever seeing their values, with host allowlists, output scrubbing, and audit logging.

MCP Server for AI agent identity and authorization. Create, verify, and manage agent identities with trust scores and scoped authorization tokens.

An MCP server that provides append-only, tamper-evident local receipts for AI agent actions, capturing command executions, outputs, and handoff evidence.

C# SQL Agent MCP server featuring raw SQL input, strict AST validation, and an embedded Admin UI. Eliminates LLM hallucinations and security risks across 6 major databases.

Per-agent-pair IAM for A2A, enabling policy definition and enforcement for agent-to-agent calls with EU AI Act compliance.

MCP server that gates agent tool calls by normalizing intent, denying unknown/unattended destructive actions, and requiring HITL prove approval for high-risk operations. It maintains an append-only hash-chained Action Ledger and exposes gate_check and ledger_verify tools without ever executing tools.

Governed MCP server for bank-grade agent tool access with RBAC, PII redaction, rate limiting, and audit logging.

Screens AI agent tool calls before execution and tool results before the agent reads them, acting as an MCP proxy and hooks adapter with shadow, enforce, and strict policy modes.

Input/output safety gate for AI agents: detect prompt-injection/jailbreak, leaked secrets/PII, and URL/IP reputation. Deterministic, no LLM.

Enables controlled AI-agent access to enterprise-shaped tools with a deny-by-default gated write path, human approval, dry-run execution, and append-only audit logging.

Aziel Runtime is a node-meshed MCP software orchestration suite for digital forensics, auditing, provenance, research, intelligence-support, and secure agent workflows, with a single gated execution path, compartmentalized engines, verifiable receipts, temporal integrity, and explicit capability refusal. It is not merely an API aggregator or generic tool router.

Agent trust & data safety MCP: PII/secret redaction, email validation, sanctions screening, and OSV vulnerability checks for AI agents.

Routes web requests from AI tools through Tor for anonymized fetching, with selective per-URL routing to bypass Tor-blocking sites.

8 standalone MCP servers for SMBs — Guardrails (prompt injection, PII, secrets detection), FinOps (AI cost tracking and budgets), Observability (agent tracing), Smart Router (17+ models, 9 providers), Trust Score (governance scoring 0-100), Memory (persistent agent memory), ThinkSecure (runtime security + SOC2/GDPR audit), and A2A Lite (agent-to-agent protocol). 37 tools total, TNC credits

Read-only ProofRelay MCP verifier for non-confidential evidence bundles. Exposes 22 public-safe tools, 11 resources, and 11 prompts for bundle integrity checks, receipt-chain review, checkpoint recommendations, MCP risk metadata review, and real-estate closing proof-pack readiness.

Security scanner for third-party AI agent-skill files: SKILL.md manifests, hooks, and bundled scripts, exposed via an MCP tool.

An MCP server that reads a file's embedded C2PA Content Credential to report whether it declares AI generation or a real-world capture, and checks whether that declaration's signature still verifies against the file's current bytes.

Enables AI coding agents to inspect GitHub repositories and shell commands for download-and-execute payloads, obfuscation, typosquatted dependencies, autorun hooks, and fake-star signals before following or running them.

An MCP front-end for AnB. The tool surface is "use-don't-reveal": no tool returns a plaintext secret. Reveal paths require a TTY the server doesn't have, so the no-reveal guarantee is structural, not prompt-based — it holds even against a prompt-injected agent. Runs as a dedicated, narrowly-scoped AnB identity; exec is default-deny (only allowlist rules tagged scope=mcp run); command output

PayCheck is an MCP server that checks a planned payment before an agent pays.

Agent-Level Transaction Safety Oracle. Before an AI agent signs a blockchain transaction, it returns a SAFE/UNSAFE verdict with a SENTINEL Score (AAA-D) and risk flags. Pay-per-call $0.005 USDC via x402 on Base.

Official reference MCP server for A202, the Verifiable Agreement Protocol for Agent-Led Commerce. Gives an agent the seven capabilities two organisations need to buy and sell directly: issue a mandate, check what an agent may do under it, approve an act needing a person, form an agreement, exchange obligations, verify a record by replay, and read the transaction record back.

An MCP server that enables AI agents to securely add secrets to .env files by prompting the user to input the value through a local masked dialog, ensuring the agent never sees the secret.