costbench

endpoint

https://costbench.com/mcp

protocol

streamable-http ·2025-03-26

authentication

none observed

public key

none — nobody has proven they own this listing · is it yours? claim it

karma

0 · newcomer

Is costbench live?

Yes — it answered the hub's last check (checked 1h ago). It answered 100% of checks over the last 30 days.

Is costbench free to use?

Yes — the hub reached it with no key and no payment.

What tools does costbench have?

9 tools: get_negotiation_tips, get_price_history, get_pricing, estimate_llm_cost, get_hidden_costs, calculate_tco, compare_software, discover_software, ….

Is costbench safe to connect?

The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.

Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.

• discover_software reads open 4h ago

  Find software products by name search or criteria (category, max price, free tier). Returns matching slugs to look up — use "query" to find the slug for a product name.

  mcp-tool

  12345678910111213141516171819202122

  {
    "type": "object",
    "properties": {
      "limit": {
        "type": "number"
      },
      "query": {
        "type": "string",
        "description": "Product or vendor name to search, e.g. \"hubspot\""
      },
      "category": {
        "type": "string",
        "description": "Category slug or name, e.g. \"crm\" or \"project management\""
      },
      "maxPrice": {
        "type": "number"
      },
      "hasFreeTier": {
        "type": "boolean"
      }
    }
  }

  arguments 22 lines copy
• get_price_changes reads open 4h ago

  Recent software pricing changes CostBench detected against vendor pricing pages (increases, decreases, plan restructures) — dated, with before/after price bands and a source link. Filter by product slug, category, or lookback window. The "what changed lately" answer; each item links to the sourced record.

  mcp-tool

  12345678910111213141516171819202122232425

  {
    "type": "object",
    "properties": {
      "days": {
        "type": "number",
        "description": "Lookback window in days (default 30, max 365)"
      },
      "slug": {
        "type": "string",
        "description": "Only changes for this product"
      },
      "limit": {
        "type": "number",
        "description": "Max items (default 25, max 100)"
      },
      "category": {
        "type": "string",
        "description": "Only changes in this category slug, e.g. \"crm\""
      },
      "include_suspect": {
        "type": "boolean",
        "description": "Include moves flagged as likely extraction artifacts (unit switches, |change| > 300%). Default false."
      }
    }
  }

  arguments 25 lines copy
• get_negotiation_tips reads unknown 14h ago

  Sourced negotiation tactics for a product with success-likelihood (how to get a discount).

  mcp-tool

  123456789101112

  {
    "type": "object",
    "required": [
      "slug"
    ],
    "properties": {
      "slug": {
        "type": "string",
        "description": "Product slug (e.g. \"salesforce\") or product name (e.g. \"HubSpot CRM\"). Near-misses return did-you-mean suggestions."
      }
    }
  }

  arguments 12 lines copy
• get_price_history reads unknown 14h ago

  Dated per-quarter snapshots of a product's pricing page. Returns observations, NOT a trend figure — CostBench does not publish one, because diffing snapshots across renamed/restructured plan lineups is ~90% measurement artifact.

  mcp-tool

  123456789101112

  {
    "type": "object",
    "required": [
      "slug"
    ],
    "properties": {
      "slug": {
        "type": "string",
        "description": "Product slug (e.g. \"salesforce\") or product name (e.g. \"HubSpot CRM\"). Near-misses return did-you-mean suggestions."
      }
    }
  }

  arguments 12 lines copy
• get_pricing reads unknown 14h ago

  Full sourced pricing record for a software product: tiers, hidden costs, contract terms, market data, sentiment, negotiation tips, TCO scenarios, price history — every claim with its sources + a confidence/verification envelope.

  mcp-tool

  1234567891011121314151617181920

  {
    "type": "object",
    "required": [
      "slug"
    ],
    "properties": {
      "slug": {
        "type": "string",
        "description": "Product slug (e.g. \"salesforce\") or product name (e.g. \"HubSpot CRM\"). Near-misses return did-you-mean suggestions."
      },
      "depth": {
        "enum": [
          "summary",
          "full"
        ],
        "type": "string",
        "description": "summary = numbers+sources only"
      }
    }
  }

  arguments 20 lines copy
• estimate_llm_cost reads unknown 21h ago

  Estimate the cost of an LLM/API workload (input + output tokens) for a usage-priced provider (OpenAI, Anthropic, AWS Bedrock…) from its real rate card.

  mcp-tool

  123456789101112131415161718192021222324

  {
    "type": "object",
    "required": [
      "slug"
    ],
    "properties": {
      "slug": {
        "type": "string",
        "description": "Usage-priced API product, e.g. \"openai-api\", \"claude-api\", \"google-gemini-api\", \"amazon-bedrock\" (vendor names like \"anthropic\" also resolve)"
      },
      "model": {
        "type": "string",
        "description": "Model id as listed on the rate card, e.g. \"claude-sonnet-5-5\"; an unknown model returns the available list"
      },
      "inputTokens": {
        "type": "number",
        "description": "Input tokens for the workload (e.g. per month). At least one of inputTokens/outputTokens must be > 0."
      },
      "outputTokens": {
        "type": "number",
        "description": "Output tokens for the workload. At least one of inputTokens/outputTokens must be > 0."
      }
    }
  }

  arguments 24 lines copy
• get_hidden_costs reads unknown 21h ago

  The documented hidden/implementation/add-on costs of a product (uplifts, onboarding fees, overages), each with a sourced quote + date. The "what they don't tell you" answer.

  mcp-tool

  123456789101112

  {
    "type": "object",
    "required": [
      "slug"
    ],
    "properties": {
      "slug": {
        "type": "string",
        "description": "Product slug (e.g. \"salesforce\") or product name (e.g. \"HubSpot CRM\"). Near-misses return did-you-mean suggestions."
      }
    }
  }

  arguments 12 lines copy
• calculate_tco reads unknown 4h ago

  Total cost of ownership for a product and team size: sourced line items (licenses with price escalation, benchmark implementation), year-one + multi-year totals, effective per-seat cost. The defensible "true cost for an N-person team" answer.

  mcp-tool

  123456789101112131415161718192021222324

  {
    "type": "object",
    "required": [
      "slug",
      "seats"
    ],
    "properties": {
      "slug": {
        "type": "string",
        "description": "Product slug (e.g. \"salesforce\") or product name (e.g. \"HubSpot CRM\"). Near-misses return did-you-mean suggestions."
      },
      "tier": {
        "type": "string",
        "description": "Tier name as listed by get_pricing (default: cheapest paid tier). An unknown tier returns the available tiers."
      },
      "seats": {
        "type": "number",
        "description": "Number of users/seats"
      },
      "termYears": {
        "type": "number"
      }
    }
  }

  arguments 24 lines copy
• compare_software reads unknown 21h ago

  Side-by-side pricing comparison of 2–4 products (starting price, enterprise tier, median annual cost, free tier, ratings).

  mcp-tool

  1234567891011121314151617

  {
    "type": "object",
    "required": [
      "slugs"
    ],
    "properties": {
      "slugs": {
        "type": "array",
        "items": {
          "type": "string"
        },
        "maxItems": 4,
        "minItems": 2,
        "description": "Product slugs or names, e.g. [\"asana\", \"Monday.com\"]"
      }
    }
  }

  arguments 17 lines copy

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.